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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 66101
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to health and safety regulations

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

    occupational safety, cardiovascular disease, immigration law

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    httphttps
    -0.97
    awtextra
    -0.94
    oa̍t
    -0.85
    EDEFAULT
    -0.82
    IsContent
    -0.82
     Taktlose
    -0.81
    رشف
    -0.81
     nahilalakip
    -0.81
     فريبيس
    -0.78
    SequentialGroup
    -0.78
    POSITIVE LOGITS
     or
    0.28
    ,
    0.28
     Reverse
    0.28
     разу
    0.27
     (
    0.27
    {{
    0.26
     reverse
    0.26
     Y
    0.25
     IST
    0.25
      
    0.25
    Activations Density 0.064%

    No Known Activations