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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9634
    Prev
    Next
    INDEX
    Explanations

    specific instances of scoring plays and key events in sports games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyProduct
    -0.51
    setLayoutManager
    -0.50
     فريبيس
    -0.49
    tono
    -0.48
    opro
    -0.48
    исленность
    -0.47
     Binnen
    -0.46
    原始内容存档于
    -0.44
    PerformLayout
    -0.44
     vorg
    -0.44
    POSITIVE LOGITS
     onCreateView
    0.69
     shot
    0.68
    */].
    0.66
     interception
    0.66
     tiros
    0.63
     shots
    0.61
     headshot
    0.61
    ########.
    0.61
    يكب
    0.61
    SuppressLint
    0.60
    Activations Density 0.126%

    No Known Activations