© 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. 16219
    Prev
    Next
    INDEX
    Explanations

    references to results and figures in the text

    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
     sp
    -0.59
    usercontent
    -0.58
     ComVisible
    -0.56
    Espèce
    -0.55
     Sp
    -0.55
    Sp
    -0.54
    /<
    -0.53
    ))
    
    -0.53
    !("
    -0.51
    '))
    
    -0.51
    POSITIVE LOGITS
     Paglinawan
    0.72
     بتاريخ
    0.68
    PerformLayout
    0.66
     通販
    0.65
     summarized
    0.65
     raiſ
    0.63
     ſur
    0.62
    withstanding
    0.62
     poffe
    0.61
     poffible
    0.60
    Activations Density 0.154%

    No Known Activations