© 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. 28-GEMMASCOPE-RES-16K
    11. 3349
    Prev
    Next
    INDEX
    Explanations

    phrases related to patent documentation and technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    U.S. Patent numbers

    np_acts-logits-general · gemini-2.0-flash

    patent numbers and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Visser
    -0.40
    
    -0.39
     Shimizu
    -0.36
     rallado
    -0.35
     interpretation
    -0.34
     ty
    -0.33
     privata
    -0.33
     Callahan
    -0.33
     unfolding
    -0.32
     dust
    -0.32
    POSITIVE LOGITS
     Patent
    0.90
    Patent
    0.87
     patent
    0.84
     patents
    0.81
     Patents
    0.78
    patent
    0.77
     PATENT
    0.74
     Inventors
    0.69
     beginnetje
    0.67
     patente
    0.66
    Activations Density 0.643%

    No Known Activations