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. 24-GEMMASCOPE-RES-16K
    6. 4364
    Prev
    Next
    INDEX
    Explanations

    phrases indicating player performance and evaluations in sports

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

    quarterback play

    np_acts-logits-general · gemini-2.0-flash

    quarterback throwing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     désolés
    -0.66
    webElementXpaths
    -0.64
    useEffect
    -0.52
    DeleteBehavior
    -0.51
    AnchorStyles
    -0.51
    astify
    -0.51
     defStyle
    -0.50
    NVIC
    -0.50
     Exactos
    -0.50
    gestone
    -0.48
    POSITIVE LOGITS
     throwing
    1.09
     Throwing
    1.03
     throw
    0.97
     throws
    0.97
     threw
    0.95
     quarterback
    0.90
     Throws
    0.89
    throwing
    0.89
     passer
    0.89
     QB
    0.87
    Activations Density 0.187%

    No Known Activations