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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 10019
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery and processes

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

    technical and engineering jargon, especially terms for machinery components, manufacturing processes, and procedural steps in industrial contexts.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.79
    RectangleBorder
    -0.71
    homonymie
    -0.71
    astify
    -0.67
     Audiodateien
    -0.64
     发表于
    -0.62
     تضيفلها
    -0.60
     autorytatywna
    -0.59
     sẻ
    -0.58
    发表于
    -0.58
    POSITIVE LOGITS
    Referanser
    0.58
     Paglinawan
    0.57
    Външни
    0.50
     prochains
    0.49
     rağmen
    0.49
    itanie
    0.49
    }:${
    0.48
    Бележки
    0.48
    scrapy
    0.48
     IBRARY
    0.47
    Activations Density 7.813%

    No Known Activations