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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2748
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section, indicating the start of new content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     autorytatywna
    -1.02
    出版年
    -0.97
    ConstraintMaker
    -0.91
    fortawesome
    -0.83
    RectangleBorder
    -0.78
     يتيمه
    -0.73
     '\\;'
    -0.73
    addCriterion
    -0.73
     iprot
    -0.73
    клопе
    -0.71
    POSITIVE LOGITS
    ↵↵
    0.62
     /*
    0.56
    														
    0.49
    /*
    0.49
    						
    0.49
     //
    0.47
    							
    0.46
    //
    0.45
     ostavi
    0.45
    ↵
    0.45
    Activations Density 0.111%

    No Known Activations