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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14728
    Prev
    Next
    INDEX
    Explanations

    function declarations and HTTP response handling in Java and ASP.NET code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fatica
    -0.54
    Aholisi
    -0.50
     manzanas
    -0.47
     Réponses
    -0.46
     pozycji
    -0.45
     Okan
    -0.45
    occuper
    -0.45
     księ
    -0.44
    ArgsConstructor
    -0.44
     polskich
    -0.44
    POSITIVE LOGITS
    WebServlet
    1.45
     HttpServlet
    1.01
    WebControls
    0.92
     Servlet
    0.90
    HttpServlet
    0.88
    Servlet
    0.85
    ServletException
    0.84
    servlet
    0.82
     servlet
    0.81
    ServletContext
    0.79
    Activations Density 0.159%

    No Known Activations