© 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. 31-GEMMASCOPE-RES-16K
    11. 3059
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to linear algebra and matrix theory

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    numerical list markers (1., 2., etc.) followed by indented content, particularly in academic or mathematical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    numbered list items and enumerated points in structured academic or technical documents.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Hart
    -0.44
     VIDEOTAPE
    -0.40
    뀜
    -0.40
    随
    -0.39
     spell
    -0.39
     medal
    -0.37
     Cath
    -0.37
     Leck
    -0.37
    putstr
    -0.37
     inten
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.58
    protoimpl
    0.57
    RenderAtEndOf
    0.57
     disambiguazione
    0.54
     ujednoznacz
    0.50
     تضيفلها
    0.48
     verantwoorde
    0.47
     OFDb
    0.47
    ContextHolder
    0.45
     ModelExpression
    0.45
    Activations Density 0.133%

    No Known Activations