© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6773
    Prev
    Next
    INDEX
    Explanations

    references to "old" or "ancient" items or concepts

    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
    :✨
    -0.69
     للاسماء
    -0.52
    wußt
    -0.46
    rungsseite
    -0.43
     BigNumberish
    -0.39
    epam
    -0.39
    ագրություններ
    -0.38
    pyx
    -0.36
     protoimpl
    -0.35
    schirm
    -0.35
    POSITIVE LOGITS
     old
    3.55
    old
    2.92
     OLD
    2.73
    Old
    2.72
     Old
    2.67
    OLD
    2.47
     vecchi
    2.45
     older
    2.44
     viejo
    2.42
     vieux
    2.38
    Activations Density 1.139%

    No Known Activations