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. 10095
    Prev
    Next
    INDEX
    Explanations

    instances of "bu" and its variations in various contexts

    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
     שוליים
    -0.67
    }{*}{
    -0.64
    fael
    -0.57
     समीक्षक
    -0.56
    ValueStyle
    -0.55
    ᅠ
    -0.54
    fml
    -0.53
     bezeichneter
    -0.53
    ADELPHIA
    -0.52
     porte
    -0.50
    POSITIVE LOGITS
    Bu
    0.75
     Bu
    0.73
     bu
    0.65
    bu
    0.63
     Bux
    0.62
     doInBackground
    0.59
     Bü
    0.59
     Bunt
    0.57
     Budi
    0.57
    utuhkan
    0.56
    Activations Density 0.068%

    No Known Activations