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. 20-GEMMASCOPE-RES-16K
    6. 436
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related elements within programming or markup languages

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

    XML layout and programming attributes, specifically Android UI configuration details.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    jsxFileName
    -0.53
    kuuta
    -0.41
    drawSprites
    -0.40
    <eos>
    -0.38
    └──
    -0.38
    AddTagHelper
    -0.37
    endregion
    -0.37
    centralwidget
    -0.37
     etc
    -0.36
    Bronnen
    -0.36
    POSITIVE LOGITS
     themſelves
    0.54
    
    0.49
    httphttps
    0.49
     clearColor
    0.45
    Geplaatst
    0.44
    见状
    0.44
     geſch
    0.44
     padrões
    0.44
     uſed
    0.44
    Ծանոթ
    0.44
    Activations Density 0.011%

    No Known Activations