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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24328
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures, particularly in the context of language handling and database management

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

    programming boolean logic

    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
    HtmlAttribute
    -0.46
    RenderAtEndOf
    -0.45
    Count
    -0.41
     Réponses
    -0.39
     count
    -0.38
    PyObject
    -0.37
     怎样
    -0.36
    count
    -0.36
    出版年
    -0.36
     jsPsych
    -0.35
    POSITIVE LOGITS
    әрмәләр
    0.48
    CloseOperation
    0.46
    protoimpl
    0.46
    vician
    0.45
    $_['
    0.41
     Dolor
    0.40
     ох
    0.38
     independently
    0.38
    outSlope
    0.37
    DbType
    0.37
    Activations Density 0.065%

    No Known Activations