Intel Loihi 2 and what a neuromorphic chip in orbit would actually run
Intel Loihi 2 carries up to one million programmable spiking neurons on a single chip. That figure comes from Garrick Orchard, E. Paxon Frady, and Mike Davies in the 2023 paper describing the architecture (arXiv:2304.01210), which also specifies 120 million synapses, 128 neuromorphic cores arranged in a two-dimensional mesh, and fabrication on the Intel 4 process. Those numbers matter for the consciousness question, not the efficiency question, because what distinguishes Loihi 2 from its predecessor is not scale but programmability. The original Loihi chip fixed its neurons as leaky integrate-and-fire (LIF) units. Loihi 2 exposes microcode so researchers can run any stateful spiking model, including the Izhikevich neuron and the Resonate-and-Fire neuron, without changing the hardware. That is the feature that makes the chip worth thinking about carefully, and the feature that orbital hardware coverage cannot address. The question is whether an architecture that can express different neuron models is relevant to consciousness research, and the answer has to start with what those models actually differ on.
Why LIF neurons are insufficient for the substrate question
The Neutral Core runs Nengo and its neurons are LIF units. That choice is defensible for a simulation: LIF is computationally tractable and captures the basic threshold-and-reset dynamics of biological neurons. The limitation is that LIF neurons fire in an all-or-nothing pattern determined by a single membrane time constant and a fixed threshold. Biological neurons are far more heterogeneous. Some respond preferentially to the onset of a stimulus and then adapt. Some resonate at particular input frequencies. Some produce bursts. The Izhikevich model, introduced by Eugene Izhikevich in his 2003 paper in IEEE Transactions on Neural Networks (DOI: 10.1109/TNN.2003.820440), reproduces fourteen distinct firing patterns seen in cortical recordings, including regular spiking, fast spiking, intrinsically bursting, and chattering neurons, using only two differential equations and four parameters. That computational tractability combined with biological breadth is why the Izhikevich model is the standard comparison point when researchers want to go beyond LIF without the full complexity of Hodgkin-Huxley dynamics. The mathematical and dynamical argument for why these non-LIF models are necessary for stable recurrent consciousness criteria is explored in Eugene Izhikevich and why the choice of spiking neuron model matters.
The relevance to consciousness is not abstract. Theories that ground consciousness in specific temporal dynamics, Victor Lamme’s recurrent processing theory and the Global Workspace Theory of Stanislas Dehaene and Jean-Pierre Changeux, predict that the pattern of spiking activity, not just its presence, determines whether a system is doing the relevant computation. The August 2026 post on spiking neural networks and recurrent processing found that sustained gamma-band reverberant activity in Loihi implementations was sensitive to connectivity parameters in ways biological cortex is not. One hypothesis for that fragility is that homogeneous LIF neurons lack the diversity of temporal responses that help biological cortex maintain stable recurrent dynamics. Loihi 2’s programmable microcode makes it the first neuromorphic chip where that hypothesis can be directly tested, because researchers can now vary neuron type systematically rather than just connectivity.
What flew in orbit and what it was running
Neuromorphic hardware reached orbit before Loihi 2 was fabricated. TechEdSat-13, launched 13 January 2022 on Virgin Orbit’s Above the Clouds mission, carried a Loihi 1 chip in a Kapoho Bay USB form factor. The mission report by Marcus Murbach and colleagues (NASA Technical Reports Server, document 20220005780) describes it as the first neuromorphic processor to operate in Earth orbit. The chip ran spike-timing-dependent plasticity and spiking-network routing algorithms in the radiation environment of low Earth orbit, and the hardware performed as expected through the mission duration. The relevance for Loihi 2 is that it establishes the radiation environment as manageable for this architecture class, even though Loihi 2 itself has not flown. The Intel 4 fabrication node is not a space-qualified process, and no radiation hardening has been applied to production Loihi 2 dies. Triple modular redundancy at the software level, running three copies of a spiking network and taking the majority vote, is the mitigation researchers have described for critical applications. That adds power and area overhead that matters in a mass-constrained CubeSat.
The orbital compute missions tracked on the Orbital Compute Tracker include Starcloud-1, which ran an Nvidia H100 GPU in orbit from November 2025. The gap between a data-centre-class GPU and a neuromorphic research chip is not only in raw throughput. An H100 draws roughly 700 watts. Loihi 2 draws milliwatts per inference on sparse spiking workloads. For a satellite that generates its own power from photovoltaic panels, the milliwatt figure is the enabling one. Whether that power envelope makes neuromorphic hardware worth the engineering investment depends on what the system is doing. For a GPU running dense matrix multiplications, the power cost is inseparable from the computation. For a spiking network running event-driven sensory processing, most cores idle most of the time.
What Hala Point scales to and what it does not solve
Intel’s Hala Point system aggregates 1,152 Loihi 2 chips into a rack-mounted research system supporting 1.15 billion neurons and 128 billion synapses, announced by Intel in 2024. Human cortex contains roughly 16 billion neurons. Hala Point therefore reaches about 7 percent of cortical neuron count, a scale comparable to a small primate cortex. It is not in orbit and is not designed to be. The comparison matters for a different reason: Hala Point shows the ceiling of what the Loihi 2 architecture scales to when power and mass are not constraints. A consciousness researcher using Hala Point can ask whether networks at that scale exhibit qualitatively different dynamics from networks at single-chip scale. If the dynamics that the recurrent processing criterion requires only emerge above a certain neuron count, Hala Point is where that threshold would first become visible in a silicon system.
The limitation Intel’s team has not resolved is what Guido Piccinini raises in his neurobiophysical account of consciousness (Neurocognitive Mechanisms: Explaining Biological Cognition, OUP, 2020, ISBN 9780198866282), covered in the July 2026 post on Piccinini’s substrate argument. Piccinini argues that consciousness requires not just spiking dynamics but the specific physical processes of biological neurons, including ion channel biophysics, neurotransmitter chemistry, and astrocytic modulation. On that view, a programmable silicon spiking neuron that produces the same firing pattern as a cortical neuron is nonetheless doing a different computation, because the physical process that generates the pattern is different. Loihi 2’s programmability does not answer that challenge. It answers the question of whether a silicon system can produce the right temporal signatures. Piccinini’s challenge is whether producing the right signatures is sufficient. That remains an open question, and the Neutral Core at github.com/tlcdv/the_consciousness_ai frames the project’s own position honestly: the architecture is motivated by the hypothesis that temporal spiking dynamics matter, while acknowledging that the physical substrate question is not settled.
What a consciousness-relevant workload on Loihi 2 would need
If the Neutral Core’s LIF-based simulation were ported to Loihi 2, the immediate gain would be two things: power reduction, and access to programmable neuron models. The power reduction is measurable and real. The gain from programmable neuron models depends on what question the researcher is asking. If the question is whether adding Izhikevich neurons to the basal ganglia action selection circuit changes the system’s dynamics in ways that matter under recurrent processing theory, Loihi 2 is the first hardware where that question becomes directly answerable at scale. If the question is whether a silicon spiking network constitutes a genuine substrate for emerging consciousness, Loihi 2 does not resolve that, because the substrate question is prior to the architecture question.
What Loihi 2 does is move the investigation one step closer to empirical contact. LIF homogeneity is a confound in every experiment asking whether neuromorphic hardware satisfies consciousness criteria: if the fragility of sustained gamma activity in silicon comes from LIF uniformity rather than silicon substrate per se, then programmable neuron diversity is the variable to control. Loihi 2 is the chip on which that variable can be isolated. That is a different and more specific claim than the ones usually made about neuromorphic computing, and it is the claim that belongs to research into consciousness as a substrate-independent emergent property rather than to an orbital hardware review.
Mike Davies leads the Neuromorphic Computing Lab at Intel Labs. The Orchard, Frady, Davies et al. Loihi 2 paper is at arXiv:2304.01210. The TechEdSat-13 mission report is NTRS document 20220005780.