© 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. 328
    Prev
    Next
    INDEX
    Explanations

    numerical scores and outcomes in sports contexts

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

    Volleyball scores and related content

    np_acts-logits-general · gemini-2.0-flash

    volleyball

    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
    xelles
    -0.51
    templ
    -0.47
    ctil
    -0.46
     EconPapers
    -0.46
     Falk
    -0.44
    Queryable
    -0.43
    StateList
    -0.43
     stripped
    -0.43
    trá
    -0.43
    rodo
    -0.43
    POSITIVE LOGITS
     volleyball
    1.17
     Volleyball
    1.07
    Volleyball
    1.06
     Volley
    1.01
    🏐
    0.94
    volley
    0.88
     setter
    0.83
     Badminton
    0.78
     badminton
    0.78
    Serving
    0.75
    Activations Density 0.029%

    No Known Activations