© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15193
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical operations or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.56
    Билгалдахарш
    -0.55
    invokeLater
    -0.50
    enderror
    -0.49
    ieteur
    -0.49
    チール
    -0.47
    Искәрмәләр
    -0.46
     pleaſure
    -0.45
    XmlAccessorType
    -0.45
    ContentLoaded
    -0.45
    POSITIVE LOGITS
     ويكيپيديا
    0.51
    WriteLiteral
    0.36
    BeginContext
    0.35
     HAPPENED
    0.35
     szóci
    0.34
    ⎨
    0.34
     مخ
    0.34
     
    0.34
    verbatim
    0.34
    istoitu
    0.34
    Activations Density 0.993%

    No Known Activations