© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6383
    Prev
    Next
    INDEX
    Explanations

    specific references to notable individuals and brands

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

    Abbreviations (medical, product, or place names)

    np_acts-logits-general · gemini-2.0-flash

    Johnnie Walker, Havana Club, Muscovite mica, SBP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itoneal
    -0.47
     snippetHide
    -0.43
    BagLayout
    -0.40
     CanadaChoose
    -0.39
    Mystery
    -0.39
    <?
    -0.38
     Obrador
    -0.38
    
    -0.37
    warma
    -0.37
    Vibration
    -0.37
    POSITIVE LOGITS
    haikusbot
    0.57
    "]();
    0.52
    tonsoft
    0.52
     JpaRepository
    0.46
    ContentAsync
    0.45
    Personendaten
    0.45
    RenderAtEndOf
    0.44
     ""],
    0.44
     smtplib
    0.42
     AssemblyVersion
    0.41
    Activations Density 1.104%

    No Known Activations