© 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. 5391
    Prev
    Next
    INDEX
    Explanations

    specific structures and keywords related to responses and evaluations in a document

    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
    parsedMessage
    -0.80
     '\\;'
    -0.77
    expandindo
    -0.71
     betweenstory
    -0.71
     utafitiHapana
    -0.70
     незавершена
    -0.69
     linkovi
    -0.67
    LookAnd
    -0.64
     pleaſure
    -0.63
     ویکی‌پدی
    -0.60
    POSITIVE LOGITS
     sorella
    0.38
    genstein
    0.35
     Ajoutez
    0.30
    cjon
    0.30
     davon
    0.30
    ANTAGE
    0.29
    ann
    0.28
     ครับ
    0.28
     tevens
    0.28
    toarele
    0.28
    Activations Density 0.034%

    No Known Activations