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. 13662
    Prev
    Next
    INDEX
    Explanations

    keywords related to data manipulation and processing in programming contexts

    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
     '{@
    -0.65
    GEBURTSDATUM
    -0.61
     Monaco
    -0.55
    Monaco
    -0.55
    Réalisation
    -0.52
     mại
    -0.51
    awaiter
    -0.50
    Aktualisiert
    -0.50
     blanches
    -0.48
    livejournal
    -0.48
    POSITIVE LOGITS
     DataFrame
    0.90
    DataFrame
    0.86
     dataframe
    0.81
     pd
    0.74
     EconPapers
    0.69
     df
    0.68
     pandas
    0.67
    columns
    0.66
     columns
    0.65
    df
    0.65
    Activations Density 0.339%

    No Known Activations