© 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. 10-GEMMASCOPE-RES-16K
    11. 15834
    Prev
    Next
    INDEX
    Explanations

    references to toxicity and poisonous substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.39
    WriteLiteral
    -0.33
     Robe
    -0.33
     shawl
    -0.32
     Burt
    -0.32
     befe
    -0.32
     paille
    -0.32
     Torn
    -0.31
    Burt
    -0.31
     tackles
    -0.30
    POSITIVE LOGITS
     poison
    1.52
    poison
    1.43
    Poison
    1.38
     poisoning
    1.34
     Poison
    1.34
     poisonous
    1.33
     toxic
    1.31
     toxicity
    1.30
     Toxic
    1.27
    toxic
    1.24
    Activations Density 0.570%

    No Known Activations