© 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. 16-GEMMASCOPE-RES-16K
    11. 12861
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frustration or difficulty in achieving a task

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berdayakan
    -0.68
    :✨
    -0.65
    GEBURTSDATUM
    -0.63
     neceſſ
    -0.61
     beſ
    -0.59
     Perſ
    -0.57
    endpush
    -0.57
     Keuangan
    -0.56
     propOrder
    -0.56
     nahilalakip
    -0.56
    POSITIVE LOGITS
     Incidentally
    0.42
     partake
    0.40
     contd
    0.34
     whatnot
    0.33
     pertaining
    0.32
     vouch
    0.31
    🏽
    0.30
    倘
    0.29
     чего
    0.29
    余談
    0.29
    Activations Density 2.053%

    No Known Activations