© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    references to casual sexual encounters and provocative language

    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
     perhaps
    -0.54
    其
    -0.53
    ใด
    -0.52
    perhaps
    -0.52
     insbesondere
    -0.51
     initially
    -0.51
    Perhaps
    -0.47
     pungkasnya
    -0.45
     szczególnie
    -0.44
     typelib
    -0.44
    POSITIVE LOGITS
     shit
    0.73
     bitches
    0.69
     stuff
    0.66
     drugs
    0.66
     fucking
    0.65
     stupid
    0.64
     porn
    0.63
     fuckin
    0.62
     crap
    0.62
     assholes
    0.60
    Activations Density 0.593%

    No Known Activations