© 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. 94869
    Prev
    Next
    INDEX
    Explanations

    references to armed individuals or groups

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

    armed + noun (forces, robbery, conflict, men)

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     maternidade
    -0.54
     DETAIL
    -0.53
     onCreateView
    -0.52
    ONI
    -0.52
    DetailActivity
    -0.51
    RegressionTest
    -0.50
     Perfection
    -0.50
    ⭔
    -0.50
     Pons
    -0.50
    RectangleBorder
    -0.50
    POSITIVE LOGITS
     armed
    1.00
    Armed
    0.91
     Armed
    0.89
     armé
    0.82
     воору
    0.69
     faſt
    0.68
    armed
    0.65
     armados
    0.64
     armée
    0.63
     armado
    0.61
    Activations Density 0.007%

    No Known Activations