Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3480
    Prev
    Next
    INDEX
    Explanations

    code structures and function calls within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Utf
    -0.47
    جغرافيا
    -0.47
     Aru
    -0.46
    MessageWindow
    -0.44
    aarrggbb
    -0.44
     Bioaccumulative
    -0.44
     Wikimedijinoj
    -0.44
     incom
    -0.43
    raeli
    -0.43
    vertible
    -0.43
    POSITIVE LOGITS
     typelib
    0.65
     OFDb
    0.49
     виправивши
    0.49
     intptr
    0.47
    WebElementEntity
    0.44
     CreateTagHelper
    0.43
     ""],
    0.40
     ExecuteAsync
    0.37
    horabuena
    0.37
     Económica
    0.37
    Activations Density 0.159%

    No Known Activations