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. 2791
    Prev
    Next
    INDEX
    Explanations

    references to Java interfaces and their implementations

    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
    цездатний
    -0.60
    HtmlAttribute
    -0.59
    RequestOptions
    -0.56
    ChatColor
    -0.55
    makeConstraints
    -0.53
    قایناقلار
    -0.51
     trouvez
    -0.51
     GoogleFonts
    -0.50
    xically
    -0.49
     ngân
    -0.49
    POSITIVE LOGITS
     class
    1.46
     subclass
    1.27
     classes
    1.27
    class
    1.21
     subclasses
    1.19
     classe
    1.11
     clase
    1.06
     Class
    1.06
    subclass
    1.06
    classes
    1.01
    Activations Density 0.522%

    No Known Activations