© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 72738
    Prev
    Next
    INDEX
    Explanations

    phrases expressing emotions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    informal positive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.33
     lors
    -0.32
     Freien
    -0.29
     kobieta
    -0.29
     Auctions
    -0.27
     housse
    -0.27
     encargado
    -0.27
    各
    -0.27
     segno
    -0.26
     propre
    -0.26
    POSITIVE LOGITS
     silly
    0.93
     hilarious
    0.89
     badass
    0.88
     crazy
    0.88
     wacky
    0.84
     funny
    0.83
     sneaky
    0.82
     awesome
    0.82
     naughty
    0.82
     funky
    0.81
    Activations Density 0.067%

    No Known Activations