© 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. 59461
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and security mechanisms

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

    safe and secure

    np_acts-logits-general · gemini-2.5-flash-lite

    detects content-bearing technical or formal words — domain-specific nouns and key terms in informational writing.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ModelExpression
    -0.56
    "}")
    -0.48
     Jerusalén
    -0.47
    complexType
    -0.45
    PropertyChanging
    -0.44
     المعيارى
    -0.44
    VersionUID
    -0.43
    TagHelper
    -0.43
    Попис
    -0.43
     muualla
    -0.43
    POSITIVE LOGITS
     safeguarding
    0.49
     shielding
    0.48
     security
    0.46
     safer
    0.45
     safe
    0.43
     shield
    0.43
    security
    0.42
     Shield
    0.42
     Safe
    0.41
    Shield
    0.41
    Activations Density 0.146%

    No Known Activations