© 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. 12-GEMMASCOPE-RES-16K
    11. 8815
    Prev
    Next
    INDEX
    Explanations

    references to poison and its effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çat
    -0.46
    EndGlobalSection
    -0.36
     maș
    -0.35
     stanovnika
    -0.35
     linee
    -0.34
    verwijspagina
    -0.33
    hical
    -0.33
     arquitetura
    -0.33
     kiin
    -0.32
     stället
    -0.32
    POSITIVE LOGITS
     poison
    1.18
    poison
    1.02
     Poison
    0.97
    Poison
    0.96
     poisonous
    0.93
     poisons
    0.91
     poisoned
    0.89
     poisoning
    0.87
    毒
    0.81
     toxic
    0.75
    Activations Density 0.943%

    No Known Activations