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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 3757
    Prev
    Next
    INDEX
    Explanations

    references to poisoning and its effects

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

    references to poison, toxic substances, or harmful elements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the word "poison" and related toxic or harmful substances.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     word
    -0.44
    word
    -0.36
    oa̍t
    -0.36
    цездатний
    -0.35
    saraba
    -0.34
     Word
    -0.34
     WORD
    -0.31
     Lint
    -0.31
    SMR
    -0.31
     članak
    -0.30
    POSITIVE LOGITS
     poison
    1.73
     poisoning
    1.65
    poison
    1.62
     poisonous
    1.57
     Poison
    1.52
     toxic
    1.52
    Poison
    1.51
     poisons
    1.47
     poisoned
    1.47
     toxicity
    1.45
    Activations Density 0.361%

    No Known Activations