Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1014
    Prev
    Next
    INDEX
    Explanations

    examples of mathematical division problems asking for the remainder

    oai_token-act-pair · gemini-2.0-flash

    remainder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.69
    addContainerGap
    -0.68
     ويكيميديا
    -0.68
     rospy
    -0.67
     ddelweddau
    -0.65
     NgModule
    -0.62
    ⓧ
    -0.61
    ardown
    -0.61
     Proclamation
    -0.59
    )_/¯
    -0.59
    POSITIVE LOGITS
    ollectionView
    0.52
    ReusableCell
    0.51
    InteropServices
    0.45
    CompilerServices
    0.44
    upar
    0.44
    WidgetItem
    0.44
    艺
    0.43
     number
    0.43
    rungsseite
    0.43
    esehen
    0.42
    Activations Density 2.022%

    No Known Activations