© 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. 16-GEMMASCOPE-RES-16K
    11. 14659
    Prev
    Next
    INDEX
    Explanations

    words associated with winning and success

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

    the word "win"

    np_acts-logits-general · gemini-2.0-flash

    win or won

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.75
    audiovisuel
    -0.67
    ThroughAttribute
    -0.65
     PLWABN
    -0.63
    Jako
    -0.62
     ]}
    -0.61
    κης
    -0.60
    tanleria
    -0.60
     ͡°)
    -0.59
     ویکی‌پدی
    -0.59
    POSITIVE LOGITS
     win
    0.84
    win
    0.76
    Win
    0.75
     Win
    0.75
     Winn
    0.73
     WIN
    0.72
     Winona
    0.70
     Unwin
    0.70
     battles
    0.68
     Winning
    0.68
    Activations Density 0.090%

    No Known Activations