© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9029
    Prev
    Next
    INDEX
    Explanations

    technical terms related to Java servlet programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java code syntax and programming language constructs.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fides
    -0.40
    bildning
    -0.39
     Cavendish
    -0.38
     automation
    -0.36
     cortical
    -0.35
     piele
    -0.35
     przesz
    -0.34
     mines
    -0.34
     hyg
    -0.34
    fritt
    -0.34
    POSITIVE LOGITS
    WebServlet
    0.85
     Servlet
    0.71
    AddTagHelper
    0.66
    servlet
    0.62
     servlet
    0.62
    Servlet
    0.61
    ServletException
    0.59
    ServletContext
    0.59
     doPost
    0.55
     HttpServlet
    0.55
    Activations Density 0.218%

    No Known Activations