© 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. 20-GEMMASCOPE-RES-16K
    11. 2874
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives that describe food, cooking, and appliance efficiency

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

    superlative descriptive words like "best", "most", "easiest", "highest", "worst", etc.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Kjelder
    -0.52
    ImageContext
    -0.51
     iconLine
    -0.50
    üyada
    -0.48
    Personendaten
    -0.48
    躇
    -0.47
     durchaus
    -0.46
    Données
    -0.46
     таки
    -0.45
    有一定
    -0.45
    POSITIVE LOGITS
     smartest
    0.87
     strongest
    0.87
     brightest
    0.85
     safest
    0.81
     hardest
    0.81
     greatest
    0.81
    ziest
    0.79
     coldest
    0.78
     coolest
    0.77
     healthiest
    0.77
    Activations Density 0.298%

    No Known Activations