© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 38755
    Prev
    Next
    INDEX
    Explanations

    warnings about safety risks and potential hazards related to vehicles

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

    personal injury or death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     suavemente
    -0.41
     compleja
    -0.40
     potrzebu
    -0.40
     Tatsache
    -0.40
     comiendo
    -0.40
     Vereine
    -0.39
    bitkan
    -0.39
     Bedürfnisse
    -0.39
     interactiva
    -0.39
     protectora
    -0.39
    POSITIVE LOGITS
     injury
    0.78
     death
    0.72
     Injury
    0.65
    Injury
    0.61
     serious
    0.60
    death
    0.59
    injury
    0.58
     injuries
    0.56
     INJ
    0.56
     property
    0.56
    Activations Density 0.026%

    No Known Activations