© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5200
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code structure

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     المعيارى
    -0.91
    Diweddarwch
    -0.72
    expandindo
    -0.67
     disambiguazione
    -0.65
    Tikang
    -0.63
     wireType
    -0.63
     StringTokenizer
    -0.62
    存于互联网档案馆
    -0.61
    UnusedPrivate
    -0.61
    دانشنامهٔ
    -0.59
    POSITIVE LOGITS
     התח
    0.34
    `
    0.32
    weza
    0.31
    上
    0.30
     harn
    0.30
     воспользова
    0.30
    A
    0.30
    向
    0.30
    <code>
    0.30
    ``
    0.30
    Activations Density 0.349%

    No Known Activations