© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    questions directed towards an audience, specifically asking for opinions or actions

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

    rhetorical questions or interrogative phrases with "do you" construction.

    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
    CloseOperation
    -0.93
     مشين
    -0.75
    RegressionTest
    -0.68
     propOrder
    -0.68
    ConstraintMaker
    -0.66
    ագրություններ
    -0.65
     jspb
    -0.63
    ThroughAttribute
    -0.63
     arşivlendi
    -0.61
    findpost
    -0.60
    POSITIVE LOGITS
     ever
    0.54
    ?
    0.40
     være
    0.40
     be
    0.39
    Being
    0.39
     being
    0.38
     شوند
    0.37
     باشند
    0.35
     EVER
    0.34
    ?<
    0.34
    Activations Density 0.226%

    No Known Activations