© 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. 41-GEMMASCOPE-RES-16K
    11. 7935
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases indicating connections between ideas or statements

    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
    IVEREF
    -0.72
    прочем
    -0.61
    itattu
    -0.59
     Grüsse
    -0.56
    ValueStyle
    -0.56
    postsleuth
    -0.54
    Such
    -0.53
     endblock
    -0.53
    quelize
    -0.50
     actuels
    -0.50
    POSITIVE LOGITS
     obviously
    0.96
     certainly
    0.83
     everybody
    0.83
     especially
    0.78
     particularly
    0.77
     again
    0.75
     you
    0.72
     part
    0.72
     people
    0.71
     oftentimes
    0.71
    Activations Density 0.195%

    No Known Activations