© 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. 13-GEMMASCOPE-RES-65K
    6. 16339
    Prev
    Next
    INDEX
    Explanations

    coding and programming-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeiti
    -0.70
    insel
    -0.69
    tre
    -0.66
    jsdelivr
    -0.64
     Ily
    -0.63
     église
    -0.61
    ="">
    
    -0.61
     cafes
    -0.61
    >");
    
    -0.61
    بوابة
    -0.60
    POSITIVE LOGITS
    kwargs
    2.22
     kwargs
    1.85
    HtmlAttribute
    0.82
     CYTHON
    0.79
    wargs
    0.79
     Whip
    0.78
     Khur
    0.77
     Cranston
    0.71
    rtl
    0.69
    SPATH
    0.69
    Activations Density 0.005%

    No Known Activations