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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8204
    Prev
    Next
    INDEX
    Explanations

    coding terminology and structure

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

    Document structure markers that indicate section boundaries, headers, or formatting elements in technical, legal, or academic texts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tagHelperRunner
    -0.58
     المعيارى
    -0.49
    usehen
    -0.47
     Chwiliwch
    -0.42
    RenderAtEndOf
    -0.42
     BoxFit
    -0.41
    vician
    -0.40
    msgTypes
    -0.40
    MessageTagHelper
    -0.39
    原始内容存档
    -0.38
    POSITIVE LOGITS
     kaarangay
    0.52
    Obrázky
    0.50
     betweenstory
    0.43
    
    0.43
    ChildScrollView
    0.42
    tanleria
    0.41
    riwal
    0.40
    mögens
    0.40
    rungsseite
    0.40
    uegos
    0.38
    Activations Density 0.093%

    No Known Activations