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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10451
    Prev
    Next
    INDEX
    Explanations

    elements related to football games and player statistics

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

    sports or games

    np_acts-logits-general · gemini-2.0-flash

    game performance and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhost
    -0.60
    )}</
    -0.59
    ")){
    
    -0.59
    ']")
    -0.59
    '">
    -0.58
     mxArray
    -0.58
    ))));
    -0.57
    ()))
    
    -0.57
    alsch
    -0.57
    ])));
    -0.57
    POSITIVE LOGITS
     offensively
    0.92
     heading
    0.85
    Heading
    0.75
     entering
    0.69
    Entering
    0.67
     defensively
    0.66
     Offen
    0.65
     coming
    0.61
     headed
    0.60
     Entering
    0.59
    Activations Density 0.203%

    No Known Activations