© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 14627
    Prev
    Next
    INDEX
    Explanations

    instances of interruptions or breaks in dialogue or narration

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     goederen
    -0.33
     hautes
    -0.31
     dezelve
    -0.29
     paroisse
    -0.29
    nskap
    -0.28
     roues
    -0.28
     tuyau
    -0.27
     flechas
    -0.27
     couronne
    -0.26
     hueso
    -0.26
    POSITIVE LOGITS
     pause
    1.23
     Pause
    1.12
     pauses
    1.10
     pausa
    1.09
     pausing
    1.05
     paused
    1.01
    Pause
    0.97
     interruption
    0.91
    pause
    0.89
     interruptions
    0.88
    Activations Density 0.347%

    No Known Activations