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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6717
    Prev
    Next
    INDEX
    Explanations

    structural components of a data object or message format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ={({
    -0.52
     điều
    -0.50
    ngOn
    -0.48
    "=>$
    -0.47
    ">'+
    -0.47
    (:,:,
    -0.44
    basicConfig
    -0.42
    ")){
    -0.41
    migrationBuilder
    -0.41
    "):
    -0.41
    POSITIVE LOGITS
    VersionUID
    0.81
    IsMutable
    0.72
    WebServlet
    0.71
    featureID
    0.71
    withIdentifier
    0.70
    ngdoc
    0.70
    Atoi
    0.69
    IntoConstraints
    0.67
    jsxFileName
    0.66
    writeFieldEnd
    0.66
    Activations Density 0.253%

    No Known Activations