© 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. 50181
    Prev
    Next
    INDEX
    Explanations

    references to arrests and law enforcement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     prompt
    -0.38
     tå
    -0.38
     désolés
    -0.35
     pil
    -0.31
    bin
    -0.31
    getTable
    -0.30
    égard
    -0.30
    PickerController
    -0.30
     crisp
    -0.29
     zra
    -0.29
    POSITIVE LOGITS
    новништво
    0.59
     <>",
    0.58
     nakalista
    0.58
    Ӕ
    0.58
    UnusedPrivate
    0.58
     חיצוניים
    0.57
    Aholisi
    0.56
    ConstraintMaker
    0.56
     चीज़ों
    0.55
    Tembelea
    0.54
    Activations Density 0.005%

    No Known Activations