DiffusionGemma's steps carry vectors: a hidden, non-causal reasoning channel
DeepMind's DiffusionGemma pushes continuous vectors alongside tokens each diffusion step, and this deep dive probes whether that hidden channel does real latent reasoning. The author walks through steering, probes, and a letter-arithmetic case, finding the model represents tokens non-causally and can compute in parallel beyond token-by-token generation.