© 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. 35-GEMMASCOPE-RES-16K
    11. 14685
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and interjections within conversational speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.54
     AssemblyProduct
    -0.43
    windowFixed
    -0.39
    outSlope
    -0.38
    脚注の使い方
    -0.36
    ureusement
    -0.34
    !&
    -0.33
    ノロ
    -0.33
    leş
    -0.33
    ganu
    -0.33
    POSITIVE LOGITS
     um
    1.84
     uh
    1.75
     Um
    1.53
     umm
    1.52
    Um
    1.43
     Uh
    1.40
     erm
    1.33
    uh
    1.30
    Uh
    1.29
    Uhm
    1.25
    Activations Density 0.219%

    No Known Activations