© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10983
    Prev
    Next
    INDEX
    Explanations

    statements of agreement and disagreement in the text

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

    expressions of personal agreement or concurrence with a viewpoint or statement.

    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
    trät
    -0.35
    Referencies
    -0.34
    impres
    -0.34
     Gamb
    -0.34
     Ver
    -0.32
    hint
    -0.32
     rumor
    -0.32
    hints
    -0.32
    endurch
    -0.31
     Cris
    -0.31
    POSITIVE LOGITS
     agree
    2.08
     agrees
    1.85
     Agree
    1.84
    Agree
    1.82
    agree
    1.77
     disagree
    1.76
     agreeing
    1.73
     agreed
    1.73
     agreement
    1.66
    agreed
    1.60
    Activations Density 0.403%

    No Known Activations