© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2572
    Prev
    Next
    INDEX
    Explanations

    sports-related terminology and scores in a competitive context

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

    Standings, championships, and league rankings

    np_acts-logits-general · gemini-2.0-flash

    sports league standings and championships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.69
     defaultstate
    -0.67
    TypedDataSet
    -0.64
    Rüyada
    -0.61
     ConstraintSet
    -0.61
    GTCX
    -0.60
    новниш
    -0.58
     оригіналу
    -0.58
    Personendaten
    -0.58
    ]--;
    -0.57
    POSITIVE LOGITS
     standings
    1.04
     provisoire
    0.69
     leaderboard
    0.67
     classement
    0.63
     league
    0.62
     championship
    0.62
     unofficial
    0.57
     overall
    0.57
     mathematically
    0.57
     rankings
    0.55
    Activations Density 0.122%

    No Known Activations