© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 101476
    Prev
    Next
    INDEX
    Explanations

    terms related to security or protection, particularly involving guards or guarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     EconPapers
    -0.46
     Bix
    -0.40
     للاسماء
    -0.39
    xsi
    -0.39
     onItemClick
    -0.38
    anlagen
    -0.38
    onix
    -0.38
    xn
    -0.37
    xE
    -0.37
    Ậ
    -0.36
    POSITIVE LOGITS
     Guard
    1.28
     guard
    1.27
    guard
    1.23
     GUARD
    1.16
    Guard
    1.13
    GUARD
    1.05
     guarding
    0.91
    AuthGuard
    0.91
     Guards
    0.91
     Gard
    0.90
    Activations Density 0.004%

    No Known Activations