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. 5-GEMMASCOPE-RES-16K
    6. 3886
    Prev
    Next
    INDEX
    Explanations

    Java class and method declarations, particularly those related to GUI components and system interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.80
     Theſe
    -0.70
    AntiForgeryToken
    -0.67
    textAppearance
    -0.67
    ValueGeneration
    -0.64
    WebServlet
    -0.64
     Walkover
    -0.63
    SceneManagement
    -0.63
    ConverterFactory
    -0.63
    tonsoft
    -0.63
    POSITIVE LOGITS
    Pautan
    0.52
     ansik
    0.49
     الرخصة
    0.49
     grazia
    0.46
    BackStack
    0.44
     scolaires
    0.43
    unggulan
    0.43
     plainte
    0.42
    lève
    0.42
    afs
    0.42
    Activations Density 0.010%

    No Known Activations