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. 22383
    Prev
    Next
    INDEX
    Explanations

    assignments and initializations in programming or markup contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     inquiry
    -0.47
    ppur
    -0.43
    TRIBUN
    -0.41
     Rao
    -0.41
     Ordinance
    -0.41
     Inquiry
    -0.41
     ordinance
    -0.40
     SafeMath
    -0.39
    pédie
    -0.38
     Soler
    -0.37
    POSITIVE LOGITS
    httphttps
    1.06
    richTextPanel
    0.67
     مشين
    0.66
    TagMode
    0.65
     defaultstate
    0.59
    Personendaten
    0.58
    CodeAttribute
    0.56
     <<<<<<<<<<<<<<
    0.56
     resourceCulture
    0.56
    uxxxx
    0.55
    Activations Density 0.002%

    No Known Activations