© 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. 104861
    Prev
    Next
    INDEX
    Explanations

    references to newsletters and related content

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    C
    -0.45
    I
    -0.42
    <em>
    -0.40
    Tom
    -0.39
    Apache
    -0.38
    God
    -0.37
    Jake
    -0.36
     actor
    -0.36
    British
    -0.36
     is
    -0.36
    POSITIVE LOGITS
     newsletter
    1.20
     Newsletters
    1.11
     newsletters
    1.11
     Newsletter
    1.09
    Newsletter
    1.04
     NEWSLETTER
    0.93
    newsletter
    0.90
     betweenstory
    0.81
    ChildScrollView
    0.75
    theless
    0.71
    Activations Density 0.007%

    No Known Activations