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. 14210
    Prev
    Next
    INDEX
    Explanations

    resources related to educational self-reflection and learning activities

    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
    EDEFAULT
    -0.89
    клопе
    -0.86
    URLException
    -0.82
     surla
    -0.78
     ivelany
    -0.75
    CloseOperation
    -0.75
    AddTagHelper
    -0.70
    تقاوى
    -0.69
    ArrowToggle
    -0.67
    uxxxx
    -0.66
    POSITIVE LOGITS
     printable
    0.90
     worksheets
    0.80
     editable
    0.80
     Printable
    0.72
     worksheet
    0.71
     imprimible
    0.68
     prin
    0.66
     sheets
    0.64
     PDF
    0.63
    printable
    0.62
    Activations Density 0.083%

    No Known Activations