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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7029
    Prev
    Next
    INDEX
    Explanations

    phrases related to player evaluations and projections in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.69
     läßt
    -0.65
    webElement
    -0.60
     behaviour
    -0.56
    cyjna
    -0.56
    🏻‍♀️
    -0.56
     metálico
    -0.56
     Whilst
    -0.55
     orientation
    -0.55
    획
    -0.54
    POSITIVE LOGITS
     offseason
    0.90
     postseason
    0.83
     playoff
    0.79
     coaches
    0.78
     offensively
    0.78
     coach
    0.74
     coaching
    0.73
     players
    0.71
     teammates
    0.71
     preseason
    0.71
    Activations Density 0.818%

    No Known Activations