© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 102458
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols indicating theorems, proofs, and formal statements in mathematical text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    proofs and theorems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GOTREF
    -0.64
    новништво
    -0.61
    دانشنامهٔ
    -0.60
    XmlAccessType
    -0.57
    üyada
    -0.56
     незавершена
    -0.56
    expandindo
    -0.53
     ſever
    -0.53
     canst
    -0.52
     raiſ
    -0.52
    POSITIVE LOGITS
     Zufall
    0.40
    inį
    0.38
    @
    0.37
    dispatcher
    0.37
     įsi
    0.36
    通
    0.36
    lığı
    0.36
    agrid
    0.35
     ProtoMessage
    0.35
    VersionUID
    0.34
    Activations Density 0.915%

    No Known Activations