© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 36833
    Prev
    Next
    INDEX
    Explanations

    instances of the word "interrupt" and its variations, indicating interruptions in dialogue or narratives

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

    interrupting others

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kepem
    -0.41
     dentaire
    -0.37
    ęcz
    -0.36
     Pemer
    -0.36
     peindre
    -0.35
    kär
    -0.35
     fechas
    -0.35
     Bidang
    -0.34
     grecque
    -0.34
     économ
    -0.32
    POSITIVE LOGITS
     interrupted
    2.00
     interruption
    1.99
     interrupt
    1.95
     interrupting
    1.85
     interruptions
    1.76
     interrupts
    1.75
     Interrupt
    1.73
    interrupted
    1.63
     interrup
    1.63
    interrupt
    1.60
    Activations Density 0.012%

    No Known Activations