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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1174
    Prev
    Next
    INDEX
    Explanations

    elements related to crafting and DIY projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.10
    exitRule
    -0.88
    PMailer
    -0.88
    setVerticalGroup
    -0.87
    colgroup
    -0.86
    хьтан
    -0.84
    fromnode
    -0.81
    ViewImports
    -0.80
    RenderAtEndOf
    -0.79
     quæ
    -0.79
    POSITIVE LOGITS
     decorative
    0.77
     decoration
    0.67
     decorate
    0.61
     decorations
    0.60
     fun
    0.60
     decorating
    0.60
     DIY
    0.57
     add
    0.56
     adding
    0.55
     colorful
    0.55
    Activations Density 0.185%

    No Known Activations