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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104841
    Prev
    Next
    INDEX
    Explanations

    terms related to winning and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Cottage
    -0.49
     PSI
    -0.47
    <_>
    -0.46
     PDR
    -0.45
     cottage
    -0.44
     CRL
    -0.43
    geot
    -0.42
     DFT
    -0.42
     SDF
    -0.41
     RL
    -0.41
    POSITIVE LOGITS
     winning
    0.92
    winning
    0.92
    Winning
    0.89
     won
    0.85
     Winning
    0.85
     kemenangan
    0.81
     vinto
    0.80
     vincere
    0.80
     gagné
    0.80
    won
    0.78
    Activations Density 0.024%

    No Known Activations