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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 82013
    Prev
    Next
    INDEX
    Explanations

    the function references related to type definitions and formatting strings in programming

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

    C++ typedef statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{}
    -0.29
    saraba
    -0.27
    <bos>
    -0.26
     père
    -0.24
     aperçu
    -0.23
    こちら
    -0.22
     ense
    -0.22
    ้อย
    -0.21
    $​
    -0.21
    <eos>
    -0.21
    POSITIVE LOGITS
    typedef
    2.86
     typedef
    1.69
    RenderAtEndOf
    0.92
     autorytatywna
    0.91
     nahilalakip
    0.89
    المناصب
    0.87
    ロウィン
    0.86
     Chwiliwch
    0.82
    الحياه
    0.81
     AssemblyTitle
    0.81
    Activations Density 0.001%

    No Known Activations