© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2830
    Prev
    Next
    INDEX
    Explanations

    mentions of button UI components in code

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

    button

    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
    enumi
    -0.71
    PropertyName
    -0.53
     hình
    -0.53
     fran
    -0.51
    ourne
    -0.50
    collate
    -0.49
    XmlAccessorType
    -0.48
    enumii
    -0.48
     ApiException
    -0.48
    hasMoreElements
    -0.47
    POSITIVE LOGITS
    談社
    0.68
    AsUp
    0.64
    IBarButtonItem
    0.63
    RenderAtEndOf
    0.63
     Methuen
    0.61
     monog
    0.61
     Bayes
    0.61
     btn
    0.59
    QPushButton
    0.59
     Odysseus
    0.58
    Activations Density 0.012%

    No Known Activations