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
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11651
    Prev
    Next
    INDEX
    Explanations

    terms related to wrestling or competitive sports actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.52
     Италијани
    -0.46
    演奏
    -0.44
    遊戲
    -0.42
    getGame
    -0.42
     jugó
    -0.42
     jugado
    -0.41
    ⤹
    -0.41
    Игра
    -0.41
    initComponents
    -0.41
    POSITIVE LOGITS
     wrestling
    1.54
     wrestle
    1.42
     wrestled
    1.41
     wrestlers
    1.37
     wrestler
    1.33
     Wrestling
    1.28
    Wrestling
    1.17
     wrest
    1.08
     grappling
    0.98
     Wrestle
    0.95
    Activations Density 0.094%

    No Known Activations