© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 4188
    Prev
    Next
    INDEX
    Explanations

    terms related to health, safety, and medication

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -0.72
     or
    -0.63
    性和
    -0.63
    それとも
    -0.56
     versus
    -0.52
    docx
    -0.50
     jakim
    -0.50
     AssemblyCulture
    -0.50
     gjelder
    -0.49
    󠁢
    -0.49
    POSITIVE LOGITS
     alike
    0.85
    RuleContext
    0.72
     दोनों
    0.70
     gainera
    0.69
    alike
    0.68
    providedIn
    0.66
     lainnya
    0.63
     whatnot
    0.61
     שוליים
    0.59
     مشين
    0.58
    Activations Density 1.432%

    No Known Activations