© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 105601
    Prev
    Next
    INDEX
    Explanations

    references to cultural events and names

    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
    ReusableCell
    -0.61
    Зноскі
    -0.57
    /*
    -0.55
     CreateTagHelper
    -0.54
    VersionUID
    -0.54
    таратура
    -0.52
     <<<<<<<<<<<<<<
    -0.50
    \{\\
    -0.49
    IBOutlet
    -0.49
    optionalTypeArgs
    -0.48
    POSITIVE LOGITS
     famous
    0.38
     places
    0.35
     institu
    0.33
     subjects
    0.32
     characters
    0.32
     or
    0.32
     clim
    0.31
    ARROLL
    0.31
    famous
    0.31
     agg
    0.30
    Activations Density 0.034%

    No Known Activations