© 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. 10306
    Prev
    Next
    INDEX
    Explanations

    references to birth or being born

    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
     dataSnapshot
    -0.68
    UserScript
    -0.58
    elemField
    -0.56
    **********/
    -0.55
    /');
    -0.54
    slidesToShow
    -0.54
    getActiveSheet
    -0.53
     "");
    
    -0.52
    ()];
    -0.52
    TintMode
    -0.52
    POSITIVE LOGITS
    visual
    0.94
    VISUAL
    0.78
    AndEndTag
    0.75
     visual
    0.73
     visualize
    0.71
     visualizing
    0.68
     Visual
    0.66
     VISUAL
    0.66
     born
    0.66
    Visual
    0.65
    Activations Density 0.061%

    No Known Activations