© 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. 3-GEMMASCOPE-RES-16K
    11. 14499
    Prev
    Next
    INDEX
    Explanations

    terms related to toxicity and harmful substances

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     дописавши
    -1.13
     كومونز
    -0.95
     noqa
    -0.81
    IBar
    -0.79
    +#+
    -0.79
     تضيفلها
    -0.79
     AssemblyCompany
    -0.78
    Hozzáférés
    -0.76
    SqlSession
    -0.76
     surla
    -0.75
    POSITIVE LOGITS
     toxic
    2.58
    toxic
    2.51
     Toxic
    2.48
    Toxic
    2.35
     toxicity
    2.31
     TOXIC
    2.20
     Toxicity
    2.02
    TOXIC
    1.95
     poisonous
    1.89
     toxins
    1.87
    Activations Density 0.174%

    No Known Activations