Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4788
    Prev
    Next
    INDEX
    Explanations

    HTML code elements or structures, particularly those related to configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     الاطلاع
    -0.59
     Ste
    -0.43
     steam
    -0.42
     Ror
    -0.38
    luis
    -0.38
     ExecuteAsync
    -0.38
    opot
    -0.38
     transform
    -0.37
     imper
    -0.37
     bagay
    -0.37
    POSITIVE LOGITS
    MENAFN
    0.83
    Datuak
    0.81
     informée
    0.77
    новниш
    0.73
    inafter
    0.72
     }}{\
    0.70
    BagConstraints
    0.69
    ()]);
    0.69
     незавершена
    0.67
    saraba
    0.66
    Activations Density 0.475%

    No Known Activations