© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96520
    Prev
    Next
    INDEX
    Explanations

    specific biochemical compounds and proteins related to cellular processes

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

    poison, toxin, and biological agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    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
    -0.32
     stationnement
    -0.30
     adicional
    -0.29
     Walkover
    -0.29
     valiente
    -0.28
     nær
    -0.28
     fréquent
    -0.28
     caucho
    -0.27
     yumu
    -0.27
     solito
    -0.27
    POSITIVE LOGITS
    WireFormatLite
    1.04
     poison
    1.03
    poison
    0.98
     poisonous
    0.91
     poisoning
    0.90
    TypedDataSet
    0.89
     toxin
    0.86
     poisons
    0.86
    Poison
    0.85
     toxicity
    0.84
    Activations Density 0.192%

    No Known Activations