© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8964
    Prev
    Next
    INDEX
    Explanations

    details related to patent applications and their associated information

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

    "patent" and its related context

    np_acts-logits-general · gemini-2.0-flash

    patent filing and application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inton
    -0.51
    FontOfSize
    -0.49
    litude
    -0.45
    Beats
    -0.45
     Kristine
    -0.45
     CreateTagHelper
    -0.44
    resco
    -0.44
     Disqus
    -0.43
    Aggregator
    -0.43
     Spas
    -0.43
    POSITIVE LOGITS
     patent
    2.11
     Patent
    1.98
    Patent
    1.83
    patent
    1.80
     patents
    1.78
     PATENT
    1.71
     Patents
    1.58
     patented
    1.54
    专利
    1.39
     patente
    1.34
    Activations Density 0.313%

    No Known Activations