Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 10
    Prev
    Next
    INDEX
    Explanations

    numerical values related to legal cases or regulations

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

    numerical identifiers or codes related to research citations

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

    numbers after or within parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.98
     ModelExpression
    -0.76
    NewGuid
    -0.68
    strokeStyle
    -0.68
     ब्रेकडाउन
    -0.65
    SourceChecksum
    -0.65
    🏻
    -0.64
     Assyrian
    -0.64
    InSection
    -0.63
    DeleteBehavior
    -0.63
    POSITIVE LOGITS
    ']):
    0.70
    "):
    
    0.69
    ']))
    0.66
    "]];
    0.64
    ")))
    0.64
    "));
    
    0.63
    "];
    
    0.62
    ")));
    
    0.62
    ())))
    0.61
    "]))
    0.61
    Activations Density 0.231%

    No Known Activations