© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 39696
    Prev
    Next
    INDEX
    Explanations

    parentheses and formatting tokens related to code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibatis
    -0.68
    oeil
    -0.67
    BagConstraints
    -0.58
    ète
    -0.58
    AndEndTag
    -0.56
     Purposes
    -0.56
     Shaffer
    -0.55
    FLT
    -0.54
    acher
    -0.53
    MRC
    -0.53
    POSITIVE LOGITS
     Мексичка
    0.73
    ScopeManager
    0.69
    tamment
    0.69
    \{\\
    0.69
     Efq
    0.67
    contentLoaded
    0.67
     تضيفلها
    0.62
    argout
    0.62
     itſelf
    0.61
    +#+#
    0.61
    Activations Density 0.004%

    No Known Activations