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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12735
    Prev
    Next
    INDEX
    Explanations

    elements related to file paths and their manipulation in code

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

    Code snippets including the word "path"

    np_acts-logits-general · gemini-2.0-flash

    path.resolve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.59
    WebServlet
    -0.57
    +#+
    -0.54
    CheckedChanged
    -0.50
    expandindo
    -0.48
    ۣ
    -0.48
    Rüyada
    -0.46
    umd
    -0.46
     doGet
    -0.46
     Bek
    -0.46
    POSITIVE LOGITS
     path
    1.30
     Path
    1.30
    Path
    1.27
    path
    1.14
     PATH
    1.13
     paths
    1.12
     Paths
    1.08
     getPath
    1.06
    PATH
    1.04
    getPath
    1.02
    Activations Density 0.069%

    No Known Activations