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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16044
    Prev
    Next
    INDEX
    Explanations

    instances of gathering or assembling in a communal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     estekak
    -0.56
     fieltro
    -0.55
    RenderAtEndOf
    -0.54
     الرياضيه
    -0.52
     lenker
    -0.52
    httphttps
    -0.52
    Diweddarwch
    -0.47
    
    -0.44
    Dichloropropane
    -0.44
     հղումներ
    -0.44
    POSITIVE LOGITS
     attendance
    0.72
     audience
    0.69
     spectators
    0.61
    audience
    0.57
     Attendance
    0.56
    attendance
    0.55
     spectator
    0.54
     audiences
    0.54
     spect
    0.54
     Audience
    0.53
    Activations Density 0.175%

    No Known Activations