© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10758
    Prev
    Next
    INDEX
    Explanations

    references to IRS notices or tax-related inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.83
     autorytatywna
    -0.73
     pinulongan
    -0.69
     مشين
    -0.66
    WithIOException
    -0.64
     initComponents
    -0.63
    RectangleBorder
    -0.63
    IBOutlet
    -0.61
    elemField
    -0.60
    Autoritní
    -0.60
    POSITIVE LOGITS
    <!--[
    0.35
     overall
    0.28
     tia
    0.28
    ớt
    0.27
     Middle
    0.26
     пер
    0.25
     raad
    0.25
     podjela
    0.24
     besser
    0.23
     nhan
    0.23
    Activations Density 1.180%

    No Known Activations