© 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. 0-GEMMASCOPE-RES-16K
    11. 8235
    Prev
    Next
    INDEX
    Explanations

    conjunctions linking multiple clauses or items together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.36
    WaitGroup
    -0.35
    webElement
    -0.32
     defaultstate
    -0.30
    Materiale
    -0.29
     하나
    -0.28
     nonatomic
    -0.27
     设备
    -0.27
    initComponents
    -0.27
    ddots
    -0.27
    POSITIVE LOGITS
    RenderAtEndOf
    0.58
     المعيارى
    0.55
     AssemblyCulture
    0.54
     незавершена
    0.53
    contentLoaded
    0.52
    Viited
    0.51
     AssemblyCompany
    0.50
     newOwner
    0.48
     queſta
    0.47
     Anfitrión
    0.47
    Activations Density 0.727%

    No Known Activations