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. 12411
    Prev
    Next
    INDEX
    Explanations

    phrases referring to observational studies or experimental methodologies

    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
    
    -0.90
    mybatisplus
    -0.80
    AddTagHelper
    -0.79
    uxxxx
    -0.78
    tvguidetime
    -0.78
    fjspx
    -0.76
    SequentialGroup
    -0.76
    +#+
    -0.71
    expandindo
    -0.70
    verwijspagina
    -0.70
    POSITIVE LOGITS
     belangrijkste
    0.94
     most
    0.85
     main
    0.80
    zelfde
    0.77
     principale
    0.76
     wichtigste
    0.76
     principali
    0.73
     advantage
    0.72
    selbe
    0.71
     reason
    0.70
    Activations Density 0.817%

    No Known Activations