© 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. 7980
    Prev
    Next
    INDEX
    Explanations

    specific sequences or patterns of letters or symbols

    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
    Diweddarwch
    -0.48
     gynhyrchwyd
    -0.46
    onedDateTime
    -0.44
     ब्रेकडाउन
    -0.39
    voltaic
    -0.38
    voerd
    -0.36
     незавершена
    -0.35
    Życiorys
    -0.35
    AndView
    -0.34
    Manbalar
    -0.33
    POSITIVE LOGITS
    sd
    0.85
    sv
    0.79
    sl
    0.78
    sn
    0.77
    sis
    0.73
    sb
    0.73
    sm
    0.71
    sf
    0.71
    sr
    0.70
    san
    0.69
    Activations Density 0.470%

    No Known Activations