© 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. 9-GEMMASCOPE-RES-131K
    6. 95938
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events or locations, particularly related to Las Vegas and Nevada

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

    Las Vegas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.78
    setVerticalGroup
    -0.75
     esternos
    -0.73
    AndEndTag
    -0.68
     ब्रेकडाउन
    -0.66
    Personensuche
    -0.65
    Tikang
    -0.65
     للمعارف
    -0.65
    sizeCache
    -0.63
     للاسماء
    -0.63
    POSITIVE LOGITS
     Nevada
    0.36
    FXML
    0.35
    Nevada
    0.33
     Use
    0.32
     Demand
    0.31
     hoek
    0.31
     Las
    0.31
    onClose
    0.30
     mas
    0.30
    ueltos
    0.30
    Activations Density 0.179%

    No Known Activations