© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13204
    Prev
    Next
    INDEX
    Explanations

    references to enemies or adversaries in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "enemy" or "enemies"

    np_acts-logits-general · gemini-2.0-flash

    enemy or opponent

    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
    Negative Logits
     zwiſchen
    -0.78
    ſicht
    -0.77
     erſt
    -0.76
     dieſe
    -0.73
     ſehr
    -0.72
     zuſammen
    -0.72
     dieſen
    -0.71
     beſch
    -0.70
     ſeine
    -0.70
    <unused28>
    -0.69
    POSITIVE LOGITS
     enemy
    1.67
     opponent
    1.54
     opponents
    1.48
     enemies
    1.42
    enemy
    1.34
     Enemy
    1.34
     musuh
    1.33
     opposition
    1.29
    Enemy
    1.25
     adversaries
    1.23
    Activations Density 0.315%

    No Known Activations