© 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
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14187
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and transactions

    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
     autorytatywna
    -0.80
    OGND
    -0.46
     transfieras
    -0.39
    Autoritní
    -0.35
    AsUp
    -0.34
    Pyx
    -0.33
     Lingkungan
    -0.33
     nötig
    -0.32
     habet
    -0.31
     materialen
    -0.30
    POSITIVE LOGITS
    WebElementEntity
    0.57
    ViewFeatures
    0.56
    MLLoader
    0.55
    jsxFileName
    0.53
    DockStyle
    0.53
     snippetHide
    0.52
     ویکی‌آمباردا
    0.52
    AndFlush
    0.48
    onViewCreated
    0.48
    IUrlHelper
    0.48
    Activations Density 1.977%

    No Known Activations