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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9531
    Prev
    Next
    INDEX
    Explanations

    references to pregnancy and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UNTS
    -0.67
     الرياضيه
    -0.62
    #+#
    -0.62
    htdocs
    -0.61
    றை
    -0.56
    ilaire
    -0.55
    templateUrl
    -0.55
    AutoresizingMask
    -0.54
    anguard
    -0.54
    hinged
    -0.53
    POSITIVE LOGITS
     Feather
    1.08
     feather
    0.94
    Feather
    0.88
     Resurrection
    0.83
     pumpkin
    0.82
     beard
    0.81
     resurrection
    0.80
     ghost
    0.79
     goose
    0.75
     Pumpkin
    0.74
    Activations Density 0.059%

    No Known Activations