© 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. 31-GEMMASCOPE-RES-131K
    11. 2234
    Prev
    Next
    INDEX
    Explanations

    function calls and file operations in programming code

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

    programmatic file paths

    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
    Negative Logits
    DOCTYPE
    -0.50
    OGND
    -0.47
    MENAFN
    -0.41
     препратки
    -0.41
     SqlParameter
    -0.41
    ilever
    -0.40
    findpost
    -0.40
     Censo
    -0.39
     cine
    -0.39
    ╹
    -0.38
    POSITIVE LOGITS
    autoload
    0.50
    TestingModule
    0.49
    readdir
    0.48
     protoimpl
    0.45
     surla
    0.44
     ExecuteAsync
    0.43
     import
    0.43
    interopRequire
    0.42
     modules
    0.40
     importación
    0.40
    Activations Density 0.007%

    No Known Activations