© 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. 14-GEMMASCOPE-RES-16K
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    terms related to toxicity and safety evaluations in animal studies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    LookAnd
    -0.44
     nahilalakip
    -0.42
     дописавши
    -0.35
    SerializeField
    -0.35
    BASEPATH
    -0.32
    таратура
    -0.31
    alignSelf
    -0.30
     Heff
    -0.30
     Visser
    -0.29
     sorella
    -0.29
    POSITIVE LOGITS
     Toxicological
    0.77
     toxicological
    0.74
    Ecotoxicity
    0.68
    Mutagenicity
    0.59
     toxicology
    0.59
    MemoryWarning
    0.58
    STOT
    0.58
     toxic
    0.58
     toxicity
    0.57
     kasarigan
    0.57
    Activations Density 0.424%

    No Known Activations