© 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. 20-GEMMASCOPE-RES-131K
    11. 18549
    Prev
    Next
    INDEX
    Explanations

    terms related to protective measures and safety equipment

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

    protective items and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increí
    -0.73
     mijne
    -0.71
     člov
    -0.69
    retudo
    -0.65
    umą
    -0.62
     gantung
    -0.61
     Verbrechen
    -0.61
     člove
    -0.61
     dezelve
    -0.61
     betale
    -0.61
    POSITIVE LOGITS
     protective
    0.83
    protective
    0.78
     Protective
    0.75
    Protective
    0.74
    ductory
    0.49
     defensi
    0.42
    kward
    0.40
     defensive
    0.40
     Pyrr
    0.38
    riotic
    0.38
    Activations Density 0.005%

    No Known Activations