© 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. 5273
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases that indicate quality or level of satisfaction

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

    degree, extent, amount

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     يتيمه
    -0.45
    RefreshLayout
    -0.44
     RoutedEventArgs
    -0.42
     bead
    -0.40
     AssemblyCompany
    -0.39
    httphttps
    -0.38
    WriteTagHelper
    -0.38
    orElseThrow
    -0.37
    wendigkeit
    -0.37
     createSprite
    -0.37
    POSITIVE LOGITS
     صوتيه
    0.57
    featureID
    0.48
     autorytatywna
    0.47
    NamedQueries
    0.46
    typeDefinition
    0.44
    Diweddarwch
    0.42
     amount
    0.42
     Amount
    0.42
     Wicidata
    0.41
    لينكات
    0.41
    Activations Density 0.228%

    No Known Activations