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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8342
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions, particularly those involving simplification and transformation in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ValueStyle
    -0.43
    Hentet
    -0.36
    ))));
    -0.31
    Referències
    -0.31
    はじめに
    -0.30
    ❋
    -0.29
     verband
    -0.29
    Билгалдахарш
    -0.29
    )))));
    -0.27
    Diwedd
    -0.27
    POSITIVE LOGITS
    +#+#
    1.00
    webElementXpaths
    0.71
    parsedMessage
    0.59
    MessageOf
    0.59
     iNdEx
    0.59
     Италијани
    0.57
     fieldNum
    0.54
    mybatisplus
    0.53
    setAccessible
    0.52
    keyColumn
    0.52
    Activations Density 3.468%

    No Known Activations