© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 101283
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "guard."

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

    guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{}
    -0.36
     Administrativna
    -0.35
    éraire
    -0.35
     AppComponent
    -0.34
    ของคุณ
    -0.34
    テンツ
    -0.32
     Utara
    -0.32
     testamento
    -0.32
    Eur
    -0.31
     potom
    -0.31
    POSITIVE LOGITS
    guard
    1.80
     guard
    1.37
    Guard
    1.27
    GUARD
    1.23
     Guard
    1.19
    guards
    1.18
     GUARD
    1.13
     guards
    0.95
    guarding
    0.94
    guarded
    0.83
    Activations Density 0.001%

    No Known Activations