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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8418
    Prev
    Next
    INDEX
    Explanations

    sections and mathematical formatting within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    thâu
    -0.69
     mouseY
    -0.67
     kasarigan
    -0.65
    OGND
    -0.63
    دانشنامهٔ
    -0.63
     protoimpl
    -0.60
     DataLoader
    -0.59
     Италијани
    -0.57
    Diwedd
    -0.57
     MainAxisSize
    -0.57
    POSITIVE LOGITS
    section
    1.48
    subsection
    0.85
    <b>
    0.78
    Section
    0.77
    <strong>
    0.72
    subsubsection
    0.72
    <h2>
    0.71
    <h1>
    0.69
     Section
    0.65
     section
    0.62
    Activations Density 0.006%

    No Known Activations