© 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. 4964
    Prev
    Next
    INDEX
    Explanations

    tokens related to specific identifiers or symbols, particularly those used in scientific and technical contexts

    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
     resourceCulture
    -0.98
    )");
    
    -0.95
     themſelves
    -0.93
    "])
    
    -0.92
     initComponents
    -0.88
     \\
    
    -0.88
     Meksiku
    -0.88
     endblock
    -0.87
     ―――――
    -0.86
    "]);
    
    -0.85
    POSITIVE LOGITS
     Sh
    0.57
     ש
    0.52
    ka
    0.52
    Sh
    0.52
     שב
    0.51
     she
    0.50
    kap
    0.49
     G
    0.49
     “
    0.48
     big
    0.48
    Activations Density 0.001%

    No Known Activations