© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10612
    Prev
    Next
    INDEX
    Explanations

    statistical metrics related to baseball performance

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

    Baseball statistics abbreviations and acronyms

    np_acts-logits-general · gemini-2.0-flash

    baseball strikeouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.58
    setVerticalGroup
    -0.50
    SharedDtor
    -0.45
    UrlResolution
    -0.45
    Chham
    -0.45
    RegressionTest
    -0.43
    SqlClient
    -0.42
    ScopeManager
    -0.41
    Климаты
    -0.41
    قایناق‌لار
    -0.39
    POSITIVE LOGITS
     refirió
    0.45
     Tribute
    0.44
     tribute
    0.43
     tributes
    0.42
    </tfoot>
    0.40
    getMinutes
    0.40
     admiration
    0.40
     flattering
    0.39
    EdgeInsets
    0.39
    retudo
    0.39
    Activations Density 0.172%

    No Known Activations