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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 39000
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AutoField
    -0.56
     lenker
    -0.51
    Cyfeiriadau
    -0.50
     للمعارف
    -0.50
    ArgumentParser
    -0.49
    contentLoaded
    -0.49
    PyExc
    -0.48
     MainAxisSize
    -0.47
    invokeLater
    -0.47
     بيها
    -0.46
    POSITIVE LOGITS
     nakalista
    0.60
     betweenstory
    0.49
     Meksiku
    0.46
     Herrn
    0.42
     Khusus
    0.39
    andaag
    0.38
    GEBURTSDATUM
    0.36
     Espagne
    0.35
     Conseils
    0.35
     Tunisie
    0.35
    Activations Density 0.055%

    No Known Activations