© 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. 20-GEMMASCOPE-RES-65K
    6. 511
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, especially those pertaining to data manipulation and string operations

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

    code snippets related to list or buffer manipulation in programming

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

    bin ranges and indices

    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
     kasarigan
    -0.72
    Hentet
    -0.69
    ]--;
    -0.69
     CreateTagHelper
    -0.67
    });*/
    -0.64
    '));
    
    -0.63
    )}</
    -0.62
    "}")
    -0.61
     TextAppearance
    -0.61
    ')))
    -0.60
    POSITIVE LOGITS
     further
    0.68
     continuation
    0.59
     beyond
    0.59
     after
    0.57
     onwards
    0.57
     skip
    0.56
     justice
    0.56
     jälkeen
    0.53
     дальше
    0.53
     CGRect
    0.52
    Activations Density 0.094%

    No Known Activations