© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or association

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     the
    -0.53
     chefe
    -0.36
     jefes
    -0.35
     seura
    -0.33
     a
    -0.32
     avantage
    -0.31
    avantage
    -0.30
     lotes
    -0.30
     kaupung
    -0.30
     gobern
    -0.30
    POSITIVE LOGITS
    webElementXpaths
    1.09
    TypedDataSet
    1.05
    parsedMessage
    1.04
    uxxxx
    1.01
     snippetHide
    1.00
     queſta
    0.94
    PerformLayout
    0.94
    ngdoc
    0.91
     utafitiHapana
    0.90
    WireFormatLite
    0.86
    Activations Density 0.662%

    No Known Activations