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. 20-GEMMASCOPE-RES-16K
    6. 14262
    Prev
    Next
    INDEX
    Explanations

    elements related to crowd reactions and dynamics during events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.71
    rungsseite
    -0.63
    libft
    -0.56
    setVerticalGroup
    -0.48
     malang
    -0.48
     Recherche
    -0.47
    ensiva
    -0.46
    RTHOOK
    -0.46
    struts
    -0.46
    ardo
    -0.45
    POSITIVE LOGITS
     crowd
    1.75
     audience
    1.72
     applause
    1.54
    audience
    1.47
    crowd
    1.47
     Audience
    1.46
     crowds
    1.44
    Audience
    1.41
     Crowd
    1.35
    Crowd
    1.33
    Activations Density 0.134%

    No Known Activations