Model techniques map
Techniquesmodel architecturenormalization & residual

implementation detail · filed under model architecture

Per-Branch Scalar Write Gate

A Gated Residual write mechanism that applies one data-dependent scalar to each branch.

Also called Per-branch scalar residual write gate, write gate.

sources
2
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

the write gate is a single scalar per branch

coremodel architecturein Qwen3.8-Flash-NextQwen

The block output is written to every branch through one data-dependent scalar per branch

coreunclearin Qwen3.8-Flash-NextQwen

Filed alongside

Other methods under model architecture :: normalization & residual.