© 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 EvalsExportsinterp-engineNEWAPI 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. 2316
    Prev
    Next
    INDEX
    Explanations

    the beginning of the document or sections marked by a starting tag

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

    system error codes and financial dividends

    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
    AddTagHelper
    -0.55
    Coup
    -0.54
     Réalisation
    -0.52
    AsUp
    -0.51
     MARSH
    -0.49
     himſelf
    -0.48
     Construct
    -0.48
     GENERATED
    -0.48
    ান
    -0.47
    Normally
    -0.47
    POSITIVE LOGITS
    )]);
    0.69
    ')")
    0.65
    ?";
    0.64
    ,:);
    0.64
    }{*}{
    0.64
     OBITUARY
    0.62
    }`).
    0.60
    '";
    0.60
     UIImage
    0.59
    ]";
    0.59
    Activations Density 0.020%

    No Known Activations