© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3423
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the creation and management of effects within specified zones

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

    error, conditions, nuclear, as

    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
    Personensuche
    -1.02
     betweenstory
    -0.83
    _));
    -0.82
     initComponents
    -0.81
    )");
    -0.80
     '\\;'
    -0.79
    )";
    -0.79
    %?
    -0.78
    ."</
    -0.77
     resourceCulture
    -0.77
    POSITIVE LOGITS
     “
    0.70
     «
    0.70
     "
    0.67
     ''
    0.54
    :
    0.53
     '{}
    0.51
     \
    0.50
     ‘
    0.50
     "%
    0.47
     {
    0.47
    Activations Density 0.032%

    No Known Activations