© 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. 21-GEMMASCOPE-RES-16K
    11. 10505
    Prev
    Next
    INDEX
    Explanations

    intensifiers or extreme adjectives that emphasize varying degrees of quality

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     pinulongan
    -0.37
     Thủ
    -0.36
     bouche
    -0.35
     kapas
    -0.35
    jercicio
    -0.35
     incluso
    -0.35
    Interim
    -0.34
    FDP
    -0.33
     basah
    -0.33
     برانيه
    -0.33
    POSITIVE LOGITS
     extremely
    0.85
     very
    0.81
     highly
    0.77
     exceedingly
    0.71
     VERY
    0.66
     Extremely
    0.63
     incredibly
    0.62
     extraordinarily
    0.59
     Very
    0.59
     exceptionally
    0.59
    Activations Density 0.485%

    No Known Activations