© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1428
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface actions and interactions, particularly those involving buttons and navigation

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

    clickable button elements and user interface controls for navigation and interaction.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.55
    jock
    -0.52
    Viet
    -0.49
     continúas
    -0.48
     quelcon
    -0.48
     Bibi
    -0.47
    UpDown
    -0.46
    tificial
    -0.45
    Мекси
    -0.44
    DropTable
    -0.43
    POSITIVE LOGITS
     button
    1.36
    按钮
    1.01
     Button
    1.01
    button
    0.94
    ボタン
    0.93
     버튼
    0.90
     icon
    0.89
     BUTTON
    0.88
     btn
    0.88
    Button
    0.85
    Activations Density 0.206%

    No Known Activations