© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15097
    Prev
    Next
    INDEX
    Explanations

    references to Amazon Web Services (AWS) and related data-related services and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.78
     للاسماء
    -0.73
    رشف
    -0.68
    :✨
    -0.68
     lenker
    -0.67
     EconPapers
    -0.67
     Audiodateien
    -0.66
    tangentMode
    -0.62
    IntoConstraints
    -0.62
     pinulongan
    -0.61
    POSITIVE LOGITS
     UIAlert
    0.47
    AppCompat
    0.42
    toLocale
    0.42
     variétés
    0.40
    XSSF
    0.39
    synchronized
    0.39
    OwnProperty
    0.38
    HttpServlet
    0.38
    ราย
    0.37
     Evolution
    0.37
    Activations Density 2.172%

    No Known Activations