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. 1910
    Prev
    Next
    INDEX
    Explanations

    technical terms related to systems and processes involving physical properties and their effects

    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
    inthe
    -0.52
     بهذا
    -0.49
    ofthe
    -0.49
    InThe
    -0.49
    oproject
    -0.48
    шње
    -0.48
    ys
    -0.47
    ∭
    -0.47
     ihr
    -0.47
     _('
    -0.47
    POSITIVE LOGITS
     unui
    0.89
     unei
    0.80
     într
    0.73
    DoubleQuotes
    0.71
     einer
    0.69
    einem
    0.68
     referenties
    0.67
     Sebuah
    0.67
     CreateTagHelper
    0.67
     dintr
    0.65
    Activations Density 0.649%

    No Known Activations