Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12390
    Prev
    Next
    INDEX
    Explanations

    statements about natural phenomena and their explanations

    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
     дополнительных
    -0.36
     yardımcı
    -0.35
     additional
    -0.34
     kapan
    -0.33
     abenço
    -0.32
     drifted
    -0.32
     olacak
    -0.32
     alternates
    -0.31
     rağmen
    -0.31
     hacerlo
    -0.31
    POSITIVE LOGITS
     football
    1.03
     baseball
    1.00
     automobiles
    1.00
     airplanes
    0.97
     basketball
    0.96
     automobile
    0.95
     airplane
    0.93
     toothpaste
    0.93
     Shakspeare
    0.93
     aeroplane
    0.92
    Activations Density 1.216%

    No Known Activations