© 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. 20999
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to murder and violent crimes

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

    violent crimes and conflicts

    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
    kuš
    -0.37
     příslu
    -0.30
    YNAMIC
    -0.30
     megfe
    -0.29
    Hi
    -0.29
     pār
    -0.29
     superare
    -0.29
     relaxed
    -0.28
     plus
    -0.28
     unique
    -0.27
    POSITIVE LOGITS
    Tembelea
    0.78
    Datuak
    0.75
    ロウィン
    0.75
    ſelves
    0.74
     ſtate
    0.73
     ſch
    0.73
     zwiſchen
    0.73
     houſe
    0.72
    ActionCreators
    0.69
    ſſung
    0.67
    Activations Density 0.140%

    No Known Activations