© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 13689
    Prev
    Next
    INDEX
    Explanations

    the word "stretch" and its variations, indicating measurements or extents of physical paths or routes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    stretch of

    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
    Negative Logits
    Autoritní
    -0.52
    WindowConstants
    -0.35
    GEBURTSDATUM
    -0.34
     chauffage
    -0.34
     Италијани
    -0.33
     EconPapers
    -0.32
    currentColor
    -0.32
    webElementGuid
    -0.32
    mnop
    -0.31
     '\\;'
    -0.31
    POSITIVE LOGITS
     stretch
    2.08
    stretch
    1.91
     Stretch
    1.85
    Stretch
    1.71
     stretches
    1.48
     stretched
    1.07
     stretching
    1.05
    Stret
    1.05
    stret
    1.02
     Stretching
    1.00
    Activations Density 0.004%

    No Known Activations