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. 10055
    Prev
    Next
    INDEX
    Explanations

    complex relationships and trends in quantitative data

    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
     Endless
    -0.56
    Tembelea
    -0.55
     đương
    -0.54
    方便
    -0.54
     endless
    -0.53
     bodyParser
    -0.53
    ChildScrollView
    -0.53
     onOptions
    -0.51
     magari
    -0.51
    ügen
    -0.51
    POSITIVE LOGITS
     slightly
    0.92
    全体的に
    0.84
     marginally
    0.83
    slightly
    0.81
     almost
    0.81
     nearly
    0.81
     significantly
    0.80
     tended
    0.80
     trend
    0.79
     suggesting
    0.77
    Activations Density 2.924%

    No Known Activations