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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4282
    Prev
    Next
    INDEX
    Explanations

    repetitions of the article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    AsUp
    -0.72
     Himo
    -0.67
    djangoproject
    -0.57
    anmoins
    -0.56
     gereken
    -0.55
    __':
    
    -0.54
     agrí
    -0.53
     Italijanski
    -0.52
     rechnen
    -0.52
    AndEndTag
    -0.52
    POSITIVE LOGITS
     concept
    0.87
     term
    0.86
     word
    0.77
     United
    0.76
     idea
    0.68
     Internet
    0.66
     notion
    0.65
     existence
    0.64
     Americans
    0.64
     Bible
    0.63
    Activations Density 0.803%

    No Known Activations