© 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. 35-GEMMASCOPE-RES-16K
    11. 14224
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or court proceedings

    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
    WindowConstants
    -0.52
     betweenstory
    -0.50
     Italijanski
    -0.49
    uxxxx
    -0.47
    omock
    -0.41
     Савезне
    -0.41
    :][
    -0.41
     scol
    -0.40
     propOrder
    -0.40
    fromnode
    -0.38
    POSITIVE LOGITS
     saves
    1.55
     simplifies
    1.52
     simplify
    1.48
     convenience
    1.47
     rispar
    1.45
     ahorrar
    1.42
     simplifying
    1.39
     saving
    1.39
     Saves
    1.36
     ahorro
    1.34
    Activations Density 0.834%

    No Known Activations