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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73723
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "in" and related variants in code contexts

    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
    ammans
    -0.63
    esgue
    -0.62
    rungsseite
    -0.60
     nakalista
    -0.60
    expandindo
    -0.56
     icke
    -0.56
     ſch
    -0.55
    Демографія
    -0.54
     oprot
    -0.53
    PerformLayout
    -0.53
    POSITIVE LOGITS
    HasColumnType
    0.40
    basicConfig
    0.34
    AssignableFrom
    0.34
     تل
    0.34
    ReferenceEquals
    0.34
     lateinit
    0.33
     in
    0.32
    PropertyGroup
    0.31
     Grundstück
    0.30
    since
    0.29
    Activations Density 0.002%

    No Known Activations