© 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. 41-GEMMASCOPE-RES-16K
    11. 4393
    Prev
    Next
    INDEX
    Explanations

    variations of the apostrophe or possession indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lah
    -0.41
    uxxxx
    -0.39
     EconPapers
    -0.38
    XmlAccessType
    -0.38
    PREFERRED
    -0.37
    WebElementEntity
    -0.37
    AddHtmlAttribute
    -0.36
    째
    -0.36
    centa
    -0.36
    CloseOperation
    -0.35
    POSITIVE LOGITS
    ll
    2.38
    lln
    0.82
    llin
    0.79
    llus
    0.69
    llons
    0.69
    lls
    0.69
    llc
    0.68
    llan
    0.68
    lll
    0.66
     ll
    0.65
    Activations Density 0.173%

    No Known Activations