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

    Neuronpedia

    Jacobian LensNEW
    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. 41-GEMMASCOPE-RES-16K
    11. 11724
    Prev
    Next
    INDEX
    Explanations

    legal terminology and formal language used in documentation

    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
    of
    -1.88
     Of
    -1.68
    OF
    -1.63
     ofthe
    -1.62
    Of
    -1.61
    ofthe
    -1.41
     OF
    -1.38
     thereof
    -1.32
    OfThe
    -1.30
     ของ
    -1.20
    POSITIVE LOGITS
    المناصب
    0.70
     AssemblyCompany
    0.64
     autorytatywna
    0.61
     nahilalakip
    0.59
    исленность
    0.54
    Diweddarwch
    0.54
    DockStyle
    0.53
    出版年
    0.53
    uxxxx
    0.53
    findpost
    0.52
    Activations Density 1.441%

    No Known Activations