d_h_bd → glu_backward → d_value + d_gate_pre. Two weight gradient GEMMs per branch (value + gate). Upstream gradient sums both paths. VSN backward DEFERRED (W_vsn init to identity, zero gradient for now). Gradient flows to gate weights at indices 34-41. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>