chrishayuk/gemma-3-4b-it-vindex

Gemma 3 4B IT — Vindex (f16)

FFN knowledge index extracted from google/gemma-3-4b-it using LARQL.

Treats transformer FFN weights as a queryable knowledge graph — retrieval via dot-product graph walks against gate vectors, no matrix multiplication.

Usage

larql> USE "hf://chrishayuk/gemma-3-4b-it-vindex";
larql> DESCRIBE "France";

Contents

• 34 layers, 348.2K features
• Gate vectors, embeddings, down features/weights
• Attention weights, norms, tokenizer
• Probe-confirmed feature labels
• f16 precision

What is a vindex?

A vindex decouples a model's knowledge from its inference machinery. The FFN weights become a queryable graph — DESCRIBE returns typed knowledge edges, WALK traces activation paths, INFER runs graph-walk inference at 31 tok/sec on CPU.

See LARQL for the full engine.