© 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. 2583
    Prev
    Next
    INDEX
    Explanations

    references to mathematical models and computational methods

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

    names after punctuation

    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
     Dr
    -0.94
    Dr
    -0.84
     Mr
    -0.80
     dr
    -0.77
    Mr
    -0.71
    dr
    -0.66
     Mrs
    -0.66
     Ms
    -0.65
     Coach
    -0.63
     Driver
    -0.61
    POSITIVE LOGITS
    帖最后由
    0.74
     تانيه
    0.73
    tagHelperRunner
    0.71
     متعلقه
    0.71
     colleagues
    0.71
    ,:),
    0.67
     ivelany
    0.65
     collaborators
    0.63
     للمعارف
    0.61
    Filmographie
    0.60
    Activations Density 0.093%

    No Known Activations