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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 5703
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols frequently used in academic or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    commas in formal or academic writing, particularly in scientific papers and research documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @melissawessel91
    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
     InputDecoration
    -1.03
     للاسماء
    -0.94
     ModelExpression
    -0.93
    PRNewswire
    -0.92
     itſelf
    -0.91
    IsContent
    -0.91
    bootstrapcdn
    -0.90
    SequentialGroup
    -0.90
     дописавши
    -0.90
     EconPapers
    -0.89
    POSITIVE LOGITS
     etc
    0.65
     
    0.54
    ↵↵
    0.51
     ,
    0.50
     AND
    0.48
    ↵
    0.48
      
    0.47
     e
    0.46
    .....
    0.45
    jav
    0.45
    Activations Density 0.132%

    No Known Activations