© 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. 27-GEMMASCOPE-RES-16K
    11. 6778
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as methods, function calls, and conditional statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     gyhoeddwyd
    -0.63
    bibfield
    -0.52
    lapsingToolbar
    -0.49
     unknownFields
    -0.49
    oa̍t
    -0.48
    PMailer
    -0.48
    BibitemShut
    -0.47
     виправивши
    -0.47
     AssemblyVersion
    -0.47
    出版年
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.42
    try
    0.34
    ঢ
    0.33
    googleapis
    0.32
     resourceCulture
    0.32
    exprimer
    0.30
     prøve
    0.30
    Hentet
    0.30
     train
    0.29
    ⓧ
    0.29
    Activations Density 0.298%

    No Known Activations