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. 7418
    Prev
    Next
    INDEX
    Explanations

    affirmative responses and emotional expressions

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

    Punctuation marks and response indicators in formal question-answer exchanges, particularly quotation marks at the beginning/end of responses and single-letter designations (like "A") in court testimony.

    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
    ArgumentParser
    -0.53
    ParallelGroup
    -0.52
    ChildScrollView
    -0.47
     مشين
    -0.46
    ruptedException
    -0.46
     समीक्षाएं
    -0.46
     repente
    -0.44
    ContentAsync
    -0.43
     AssemblyTitle
    -0.43
     jspb
    -0.43
    POSITIVE LOGITS
     yes
    0.70
     YES
    0.60
     Yes
    0.57
    yes
    0.55
    YES
    0.52
    Yes
    0.50
     oui
    0.45
     Nope
    0.44
    Oui
    0.43
    Personensuche
    0.43
    Activations Density 0.061%

    No Known Activations