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. 14477
    Prev
    Next
    INDEX
    Explanations

    specific terms related to averages and statistical measures

    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
     StatelessWidget
    -0.58
    ModelAdmin
    -0.57
     onCancelled
    -0.56
     unknownFields
    -0.55
     enfin
    -0.53
     disambiguazione
    -0.53
     StatefulWidget
    -0.52
    NewLabel
    -0.51
    propTypes
    -0.51
    Failing
    -0.51
    POSITIVE LOGITS
    age
    2.12
    ages
    1.99
    AGE
    1.89
    aged
    1.87
     age
    1.76
    aging
    1.60
    Age
    1.53
    AGES
    1.52
     Age
    1.51
    AGED
    1.46
    Activations Density 0.158%

    No Known Activations