© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13340
    Prev
    Next
    INDEX
    Explanations

    keywords related to poison and its effects

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

    poisons and toxins

    np_acts-logits-general · gemini-2.0-flash

    toxic and poisonous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biotite
    -0.68
    Datuak
    -0.65
     Eud
    -0.62
    stateProvider
    -0.58
     otim
    -0.56
    VIAF
    -0.55
     väli
    -0.53
     virginity
    -0.52
    Turbul
    -0.52
     coar
    -0.52
    POSITIVE LOGITS
     toxic
    1.87
     poisonous
    1.83
     poison
    1.80
     poisoning
    1.75
    poison
    1.66
     toxicity
    1.62
     poisoned
    1.61
     Toxic
    1.60
     toxins
    1.57
     poisons
    1.56
    Activations Density 0.508%

    No Known Activations