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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 15174
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "/", which may indicate segmentation or division in the text

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

    and/or conjunctions or slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     either
    -0.54
    目に
    -0.29
     Either
    -0.29
     iyong
    -0.29
    getX
    -0.28
    createObject
    -0.28
     &
    -0.27
    Either
    -0.27
     presenti
    -0.27
    LookAnd
    -0.26
    POSITIVE LOGITS
    脚注の使い方
    0.68
    AxisAlignment
    0.63
    MigrationBuilder
    0.62
    GEBURTSDATUM
    0.61
    Kjelder
    0.58
    Erreferentziak
    0.57
    تقاوى
    0.56
     kasarigan
    0.56
     الرياضيه
    0.56
    ArgumentParser
    0.55
    Activations Density 0.027%

    No Known Activations