© 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. 41-GEMMASCOPE-RES-16K
    11. 13639
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize relationships or comparisons between concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     мәкал
    -0.55
     nakalista
    -0.52
    Diweddarwch
    -0.49
    tagHelperRunner
    -0.48
    ɵɵ
    -0.46
    InjectAttribute
    -0.44
     defaultstate
    -0.43
    UserScript
    -0.42
     as
    -0.39
     AssemblyCompany
    -0.38
    POSITIVE LOGITS
     regards
    0.90
     argued
    0.72
     pointed
    0.70
     shown
    0.70
     was
    0.70
     explained
    0.68
     already
    0.67
     illustrated
    0.66
     compared
    0.63
     discussed
    0.63
    Activations Density 0.414%

    No Known Activations