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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 26773
    Prev
    Next
    INDEX
    Explanations

    structural elements of programming or markup language code

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

    visual design style

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.71
    TagMode
    -0.67
     HasFactory
    -0.67
    WaitGroup
    -0.67
    writeFieldEnd
    -0.67
     мәкал
    -0.65
     smtplib
    -0.65
     AssemblyCulture
    -0.64
    Geplaatst
    -0.63
     ویکی‌پدی
    -0.62
    POSITIVE LOGITS
     creatives
    0.42
     aesthetics
    0.42
     images
    0.42
     style
    0.41
    image
    0.39
     makeStyles
    0.39
    interactions
    0.39
    isons
    0.38
     image
    0.38
    interaction
    0.37
    Activations Density 0.000%

    No Known Activations