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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2153
    Prev
    Next
    INDEX
    Explanations

    actions and statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attro
    -0.63
     ویکی‌پدیا
    -0.63
    oplayer
    -0.62
     TextInputType
    -0.61
     itſelf
    -0.60
     دیکھیے
    -0.59
    uolo
    -0.58
    InjectAttribute
    -0.58
    KommentareTeilen
    -0.57
    ercises
    -0.57
    POSITIVE LOGITS
    gatsby
    0.57
     touchdowns
    0.57
     RBI
    0.55
     scored
    0.53
    ガニック
    0.51
    fromCharCode
    0.51
    SharedDtor
    0.51
     című
    0.49
    scored
    0.48
    dataflow
    0.48
    Activations Density 0.144%

    No Known Activations