© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14772
    Prev
    Next
    INDEX
    Explanations

    instances of the word "win" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ]').
    -0.71
    ❖
    -0.71
    WebElementEntity
    -0.68
    ]_{\
    -0.65
    ]';
    -0.65
    setTo
    -0.63
    };*/
    -0.62
    "]').
    -0.62
    ]$}
    -0.62
     complémentaires
    -0.61
    POSITIVE LOGITS
     Winona
    1.35
     win
    1.31
     Winn
    1.29
    win
    1.28
     winners
    1.23
     WIN
    1.22
    Wins
    1.19
     Winners
    1.19
     wins
    1.17
     Winslow
    1.16
    Activations Density 0.074%

    No Known Activations