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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103173
    Prev
    Next
    INDEX
    Explanations

    references to competitive matchups in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     prêtres
    -0.39
     églises
    -0.36
     informacija
    -0.34
     ledig
    -0.34
     vägen
    -0.33
     tendances
    -0.33
    chtenstein
    -0.33
     choses
    -0.33
    styrelsen
    -0.33
    plaatst
    -0.33
    POSITIVE LOGITS
     rival
    0.62
     '\\;'
    0.60
    principalTable
    0.60
    󠁢
    0.60
     melawan
    0.60
     confronting
    0.60
     lawan
    0.59
     confronted
    0.58
    NUMX
    0.58
     musuh
    0.57
    Activations Density 0.020%

    No Known Activations