© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104781
    Prev
    Next
    INDEX
    Explanations

    references to various groups, medications, and agents in a health or medical context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     OMITBAD
    -0.82
     مشين
    -0.69
    ✭✭
    -0.65
    enumii
    -0.61
    Hochspringen
    -0.60
     faſt
    -0.60
     pleaſure
    -0.59
     виправивши
    -0.58
     Efq
    -0.57
    GEBURTSDATUM
    -0.57
    POSITIVE LOGITS
     I
    0.36
     embraced
    0.36
    saga
    0.34
     that
    0.34
    ENOMEM
    0.33
    丁目
    0.33
     Malam
    0.33
     sold
    0.33
    ijnt
    0.32
     druck
    0.32
    Activations Density 0.172%

    No Known Activations