© 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. 22367
    Prev
    Next
    INDEX
    Explanations

    the beginning of sections in a document, indicated by the "<bos>" token

    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
     שוליים
    -0.80
    DataMember
    -0.78
     aDecoder
    -0.73
     Gers
    -0.72
    on
    -0.71
    ar
    -0.70
    
    -0.69
    es
    -0.67
     Ches
    -0.66
    Mem
    -0.66
    POSITIVE LOGITS
    tify
    1.06
     Tif
    1.05
    ifiers
    1.04
    ifying
    1.03
    ify
    1.03
    lifying
    1.00
    )");
    
    0.99
    IFY
    0.99
    ifies
    0.98
    ifier
    0.95
    Activations Density 0.037%

    No Known Activations