© 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 - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 6887
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new discussion or topic, typically marked by a specific format or section header

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.66
     Lindberg
    -0.61
    miec
    -0.59
    SuspendLayout
    -0.58
    jsxFileName
    -0.55
    isticated
    -0.55
    ochet
    -0.54
    السكان
    -0.54
    XmlAccessType
    -0.54
     trộn
    -0.53
    POSITIVE LOGITS
    IsContent
    0.66
    makeText
    0.56
     تضيفلها
    0.53
     समीक्षाओं
    0.48
    glBindBuffer
    0.47
     ligiloj
    0.47
    openConnection
    0.46
     SqlParameter
    0.46
    GEBURTSDATUM
    0.46
    ,\\
    0.46
    Activations Density 0.029%

    No Known Activations