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. 2609
    Prev
    Next
    INDEX
    Explanations

    occurrences of Apache Commons Math library components and their associated tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to "math" after a period

    np_acts-logits-general · gemini-2.0-flash

    apache commons math

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    getDoctrine
    -0.62
     lenker
    -0.56
    MessageTagHelper
    -0.54
    філь
    -0.51
    UserScript
    -0.51
    bootstrapcdn
    -0.51
     @"/
    -0.49
    routeProvider
    -0.49
    VIAF
    -0.48
    الإنجليزية
    -0.48
    POSITIVE LOGITS
     lombok
    0.67
    extern
    0.67
     amnio
    0.66
     Bantu
    0.65
     Arjuna
    0.64
    Setter
    0.62
     Ammon
    0.62
     Bergamo
    0.61
    Getter
    0.61
    ArgsConstructor
    0.61
    Activations Density 0.082%

    No Known Activations