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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119768
    Prev
    Next
    INDEX
    Explanations

    references to tabs and tabulation processes in a programming or data management context

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

    tabbed pane or section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    kos
    -0.50
    Kos
    -0.49
    force
    -0.49
    حياته
    -0.48
     Willi
    -0.46
    gong
    -0.46
     Kos
    -0.45
    performance
    -0.45
    eni
    -0.45
    \"");
    -0.45
    POSITIVE LOGITS
     Tab
    1.16
     tab
    1.15
    Tab
    1.09
    tab
    1.03
     TAB
    0.96
     tabs
    0.94
    Tabs
    0.91
     Tabs
    0.90
    TAB
    0.88
    tabIndex
    0.87
    Activations Density 0.011%

    No Known Activations