© 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 EvalsExportsinterp-engineNEWAPI 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. 4629
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data structures or programming constructs, particularly those involving getters and setters in a programming context

    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
    featureID
    -0.67
     unknownFields
    -0.61
    PreferredItem
    -0.61
     Administrativna
    -0.58
     Meksiku
    -0.57
    fvar
    -0.56
    windowFixed
    -0.55
    قایناق‌لار
    -0.54
    RenderAtEndOf
    -0.53
    Indication
    -0.52
    POSITIVE LOGITS
    TagMode
    0.94
    \{\\
    0.59
    SourceChecksum
    0.56
    RectangleBorder
    0.54
     الاطلاع
    0.53
    IntoConstraints
    0.52
     Roskov
    0.52
    InputBorder
    0.50
     Verkä
    0.48
    )](
    0.48
    Activations Density 0.043%

    No Known Activations