© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 194
    Prev
    Next
    INDEX
    Explanations

    references to team needs and player evaluations in sports contexts

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

    Offensive football teams and depth

    np_acts-logits-general · gemini-2.0-flash

    team talent and depth

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     doInBackground
    -0.55
    endphp
    -0.53
    涯
    -0.52
    timestamps
    -0.52
    traje
    -0.49
    utzt
    -0.48
     epithe
    -0.48
     obe
    -0.47
    Kontrola
    -0.47
    MapView
    -0.47
    POSITIVE LOGITS
     young
    0.90
     talented
    0.87
     talent
    0.85
     depth
    0.85
     roster
    0.84
     youthful
    0.78
     experienced
    0.75
    young
    0.74
     additions
    0.73
     giovani
    0.73
    Activations Density 0.206%

    No Known Activations