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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 110
    Prev
    Next
    INDEX
    Explanations

    comment or documentation syntax in code

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

    comments and metadata in code syntax

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

    code comments and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerToggle
    -0.50
    <blockquote>
    -0.49
    UnsafeEnabled
    -0.49
    InvalidProtocol
    -0.48
    mtrl
    -0.47
    ChildIndex
    -0.47
    ItemLayout
    -0.46
    F
    -0.46
    readObject
    -0.46
     pecho
    -0.45
    POSITIVE LOGITS
    //
    0.97
    -//
    0.71
     Paglinawan
    0.69
    /**
    0.67
    ConstraintMaker
    0.64
    ="//
    0.64
    ">//
    0.63
    }');
    0.62
    /~
    0.61
     CJK
    0.61
    Activations Density 0.025%

    No Known Activations