© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    references to functions and model attributes in programming contexts

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

    numerical, class, mime, double

    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
     onPostExecute
    -0.91
    httphttps
    -0.81
    KommentareTeilen
    -0.78
    UpInside
    -0.76
    FTFY
    -0.73
    Referințe
    -0.71
     AttributeSet
    -0.70
    NUMX
    -0.69
    ThroughAttribute
    -0.68
    những
    -0.68
    POSITIVE LOGITS
    че
    0.52
    дей
    0.51
    WIRE
    0.48
    ود
    0.47
    ◄
    0.47
    ло
    0.45
    ئ
    0.45
     Great
    0.45
     Vin
    0.44
    av
    0.44
    Activations Density 0.058%

    No Known Activations