Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40721
    Prev
    Next
    INDEX
    Explanations

    specific player names and performance metrics in a sports context

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

    mathematical expressions and code

    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
    ισ
    -0.31
     vi
    -0.31
     Waray
    -0.30
    enum
    -0.30
    wapV
    -0.30
     zaw
    -0.29
    external
    -0.29
    QMetaType
    -0.29
    ίσ
    -0.28
     بخ
    -0.28
    POSITIVE LOGITS
     ſta
    0.72
     myſelf
    0.68
     المعيارى
    0.65
     $_"
    0.64
    lactin
    0.62
    ⟬
    0.60
     uLocal
    0.60
     ſte
    0.60
     purpoſe
    0.60
     ſch
    0.59
    Activations Density 0.307%

    No Known Activations