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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 3610
    Prev
    Next
    INDEX
    Explanations

    phrases related to data handling and information management processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.63
    +:+
    -0.51
     GenerationType
    -0.50
     AssemblyTitle
    -0.46
    IntoConstraints
    -0.45
     AssemblyProduct
    -0.43
    TagMode
    -0.42
     مشين
    -0.42
    ViewImports
    -0.40
    homonymie
    -0.38
    POSITIVE LOGITS
     data
    3.36
     Data
    3.00
     DATA
    2.80
    data
    2.73
    Data
    2.72
    データ
    2.61
     Daten
    2.61
    DATA
    2.48
    数据
    2.44
     데이터
    2.31
    Activations Density 2.085%

    No Known Activations