© 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. 75785
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports analysis and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     prefier
    -0.39
     utafitiHapana
    -0.35
    Servidor
    -0.35
     asesinado
    -0.33
    ทย
    -0.32
     meditación
    -0.32
     requerida
    -0.32
     nødven
    -0.32
     islas
    -0.32
     cárcel
    -0.32
    POSITIVE LOGITS
     MainAxisSize
    0.75
    IntoConstraints
    0.66
    setViewportView
    0.62
    matchCondition
    0.61
    LookAnd
    0.61
    ChildScrollView
    0.60
     שוליים
    0.59
    aarrggbb
    0.59
    ніципалі
    0.59
    writeFieldEnd
    0.58
    Activations Density 0.008%

    No Known Activations