© 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. 104920
    Prev
    Next
    INDEX
    Explanations

    the start of sections or paragraphs in the text

    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
     MainAxisSize
    -0.55
    ChildScrollView
    -0.53
    guisement
    -0.47
    AsUp
    -0.46
    şört
    -0.44
    UseVisualStyle
    -0.42
     AssemblyCompany
    -0.42
    pgterms
    -0.42
     CHtml
    -0.41
    zeera
    -0.41
    POSITIVE LOGITS
    uxxxx
    1.00
     autorytatywna
    0.65
    তথ্যসূত্র
    0.61
    tvguidetime
    0.56
    Vidite
    0.53
    ResumeLayout
    0.50
    Datuak
    0.47
    :✨
    0.46
    WriteLiteral
    0.45
     Roux
    0.43
    Activations Density 0.001%

    No Known Activations