© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101816
    Prev
    Next
    INDEX
    Explanations

    various forms of parentheses used in code snippets

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

    programming control flow constructs

    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
    StoryboardSegue
    -0.82
    ScopeManager
    -0.78
    RenderAtEndOf
    -0.76
    DockStyle
    -0.75
    parsedMessage
    -0.73
    principalTable
    -0.72
     AttributeSet
    -0.71
     InputDecoration
    -0.71
     Italijani
    -0.70
    RTLI
    -0.70
    POSITIVE LOGITS
     didalam
    0.40
    (
    0.36
    if
    0.35
     pascua
    0.33
    [
    0.29
     lietu
    0.28
    (!
    0.28
    9
    0.27
    6
    0.27
     vegetación
    0.26
    Activations Density 0.010%

    No Known Activations