© 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. 12922
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and juror responsibilities

    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
     jöv
    -0.45
     незавершена
    -0.42
     الحره
    -0.37
     πισ
    -0.36
     baut
    -0.34
     praktik
    -0.33
     faudrait
    -0.32
    ผ
    -0.31
     lyder
    -0.31
     builder
    -0.30
    POSITIVE LOGITS
     headlines
    1.19
     news
    1.09
     media
    1.08
     publicity
    0.99
     newspapers
    0.96
     tabloid
    0.95
     publicized
    0.93
     headline
    0.90
     noticia
    0.88
     controversy
    0.87
    Activations Density 0.691%

    No Known Activations