© 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. 20-GEMMASCOPE-RES-131K
    11. 116808
    Prev
    Next
    INDEX
    Explanations

    technical terms related to file formats and content types

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    RegressionTest
    -0.73
    WaitGroup
    -0.62
    Aholisi
    -0.54
    IndentedString
    -0.50
    PCell
    -0.46
    كويكب
    -0.46
    SBATCH
    -0.46
    AsUp
    -0.45
    createStatement
    -0.45
     Photocase
    -0.45
    POSITIVE LOGITS
    mimetype
    0.59
    setContentType
    0.50
     skydd
    0.47
     mistura
    0.46
     civilización
    0.45
     apapun
    0.45
     TextAppearance
    0.44
    textTheme
    0.43
     Aceite
    0.43
     Sorten
    0.42
    Activations Density 0.037%

    No Known Activations