© 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. 24-GEMMASCOPE-RES-16K
    11. 2554
    Prev
    Next
    INDEX
    Explanations

    sports statistics and scores

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

    Numeric lead or advantage in a competition

    np_acts-logits-general · gemini-2.0-flash

    score lead

    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
    NameInMap
    -0.87
     AssemblyCulture
    -0.83
     referenties
    -0.74
    UrlResolution
    -0.70
    windowFixed
    -0.67
    Chham
    -0.62
     виправивши
    -0.60
    出版年
    -0.60
    setVerticalGroup
    -0.58
     defaultstate
    -0.56
    POSITIVE LOGITS
     lead
    1.52
    lead
    1.16
     advantage
    1.13
    Lead
    1.11
     leads
    1.09
     Lead
    1.05
     LEAD
    0.93
    advantage
    0.90
    leads
    0.89
    Advantage
    0.83
    Activations Density 0.127%

    No Known Activations