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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 827
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and quotation marks

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

    punctuation marks

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

    speaking, commenting, saying

    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
    RegressionTest
    -0.57
    BoxShadow
    -0.51
     letra
    -0.50
     חיצוניים
    -0.50
    fotografía
    -0.48
     estoppel
    -0.48
    ográficos
    -0.47
     inconn
    -0.47
    endpush
    -0.46
    ınır
    -0.46
    POSITIVE LOGITS
    Commenting
    1.35
    Speaking
    1.16
     commented
    1.14
     Speaking
    1.09
     commenting
    1.08
     speaking
    1.07
     Comment
    1.03
     said
    0.97
    said
    0.93
    commented
    0.88
    Activations Density 0.024%

    No Known Activations