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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6610
    Prev
    Next
    INDEX
    Explanations

    elements related to parsing and data processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.68
     surla
    -0.63
    DeleteBehavior
    -0.63
    PropertyChanging
    -0.60
     MenuView
    -0.58
    invokeLater
    -0.57
    rizona
    -0.57
    writeField
    -0.56
    +#+#
    -0.55
     transférez
    -0.54
    POSITIVE LOGITS
    iNdEx
    0.41
     berikutnya
    0.33
     bingung
    0.32
     misread
    0.31
     complicada
    0.30
     推荐
    0.30
     ček
    0.29
     télévisée
    0.29
    efficacité
    0.28
    épar
    0.28
    Activations Density 0.489%

    No Known Activations