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. 16-GEMMASCOPE-RES-16K
    6. 12832
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the installation and use of software and devices, particularly in relation to troubleshooting and functionality

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

    gadgets, inventions, and tools

    np_acts-logits-general · gemini-2.0-flash

    gadgets and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.72
     للاسماء
    -0.66
    Попис
    -0.66
     beginnetje
    -0.64
    rrggbb
    -0.62
     insuffisamment
    -0.62
    تقاوى
    -0.62
     kaynağından
    -0.61
    ViewFeatures
    -0.60
     Савезне
    -0.59
    POSITIVE LOGITS
     giz
    0.66
     device
    0.66
     product
    0.66
     solutions
    0.65
     solution
    0.65
     products
    0.63
     invention
    0.61
     devices
    0.60
    插件
    0.57
     gadget
    0.56
    Activations Density 0.607%

    No Known Activations