© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4023
    Prev
    Next
    INDEX
    Explanations

    terms related to security and safety in various contexts

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

    "Security" and "safety" related words

    np_acts-logits-general · gemini-2.0-flash

    security and safety

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ніципалі
    -0.67
     wireType
    -0.59
    addPreferredGap
    -0.55
    ónico
    -0.49
     ProtoMessage
    -0.48
     StringTokenizer
    -0.47
    BibitemShut
    -0.47
     otomatig
    -0.46
    jména
    -0.46
    depress
    -0.45
    POSITIVE LOGITS
     safety
    0.85
     seguridad
    0.78
    Safety
    0.78
     security
    0.75
     protection
    0.74
     sécurité
    0.73
     Safety
    0.73
     Sicherheit
    0.72
    security
    0.70
     segurança
    0.70
    Activations Density 0.626%

    No Known Activations