© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105217
    Prev
    Next
    INDEX
    Explanations

    URLs and their formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Not in Any Lists

    No Comments

    Negative Logits
     noqa
    -0.45
     Hud
    -0.35
     Clo
    -0.33
    Cms
    -0.33
    Vorlage
    -0.33
     NUKAT
    -0.29
     qui
    -0.29
    Ắ
    -0.27
     theft
    -0.27
     contradiction
    -0.27
    POSITIVE LOGITS
     Anſ
    0.73
    OGND
    0.70
     Reſ
    0.70
     contextLoads
    0.66
     CreateTagHelper
    0.66
     Wicidata
    0.65
    viaf
    0.64
    nologue
    0.64
    SequentialGroup
    0.62
     تضيفلها
    0.60
    Activations Density 0.054%

    No Known Activations