© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8147
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing and usage restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preprocessor directives and header guards in source code (lines beginning with `#define`, `#ifndef`, `#include`).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.60
     combineReducers
    -0.53
     estekak
    -0.52
    commutative
    -0.49
     useAppContext
    -0.49
     Conce
    -0.48
    __(/*!
    -0.48
    :✨
    -0.48
     net
    -0.48
     Balance
    -0.47
    POSITIVE LOGITS
     zelve
    0.44
     démocr
    0.43
     avoient
    0.43
     dezelve
    0.42
     étoient
    0.41
     brancas
    0.41
     esimer
    0.40
     betrek
    0.40
     conseillers
    0.40
    hésite
    0.39
    Activations Density 0.013%

    No Known Activations