Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6911
    Prev
    Next
    INDEX
    Explanations

    terms related to guarding or protection

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

    "guard" and its variations

    np_acts-logits-general · gemini-2.0-flash

    guarded or guarding

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MLLoader
    -0.53
     للاسماء
    -0.52
     sinner
    -0.35
     فريبيس
    -0.35
    muc
    -0.34
     combineReducers
    -0.33
     Addis
    -0.32
     sinners
    -0.32
     informée
    -0.32
     verz
    -0.31
    POSITIVE LOGITS
     guard
    2.02
     Guard
    1.92
     GUARD
    1.86
    guard
    1.77
    Guard
    1.75
     guarding
    1.73
     guards
    1.67
    GUARD
    1.64
     guardian
    1.54
     Guards
    1.52
    Activations Density 0.144%

    No Known Activations