© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10346
    Prev
    Next
    INDEX
    Explanations

    references to poisoning or toxic substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Toxins or poisons

    np_acts-logits-general · gemini-2.0-flash

    poisonous substance or effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.49
     word
    -0.48
    word
    -0.45
     Word
    -0.44
    saraba
    -0.41
    oa̍t
    -0.39
    Word
    -0.39
     članak
    -0.37
     Knee
    -0.36
    words
    -0.36
    POSITIVE LOGITS
     poison
    1.78
     poisoning
    1.73
    poison
    1.68
     poisonous
    1.65
     toxic
    1.63
     poisoned
    1.58
     Poison
    1.57
    Poison
    1.56
     poisons
    1.54
     toxicity
    1.48
    Activations Density 0.374%

    No Known Activations