© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    strings and path constructions in code

    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
    sizeCache
    -0.47
    phoric
    -0.39
    formik
    -0.37
    Personensuche
    -0.35
    loride
    -0.33
    )}_{
    -0.33
     Савезне
    -0.33
    Parameteri
    -0.32
     SAD
    -0.32
    bibitem
    -0.32
    POSITIVE LOGITS
    PerformLayout
    0.71
    setVerticalGroup
    0.67
    ftagPool
    0.64
    UnusedPrivate
    0.57
    IndentedString
    0.57
    endphp
    0.57
    SequentialGroup
    0.56
    prefixes
    0.54
     Einfluß
    0.52
     mengangg
    0.52
    Activations Density 0.474%

    No Known Activations