© 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. 2-GEMMASCOPE-RES-16K
    11. 8022
    Prev
    Next
    INDEX
    Explanations

    references to a specific structure or arrangement in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.71
     ujednoznacz
    -0.56
    Tembelea
    -0.56
    windowFixed
    -0.52
    Personensuche
    -0.52
    DebuggerNonUser
    -0.52
     ©️
    -0.51
    :✨
    -0.50
    interopRequire
    -0.49
    ConstraintMaker
    -0.49
    POSITIVE LOGITS
     form
    1.77
     forms
    1.05
     format
    1.05
    形式
    0.97
     bentuk
    0.91
     forme
    0.88
     formie
    0.87
     виде
    0.85
     version
    0.82
     postaci
    0.80
    Activations Density 0.233%

    No Known Activations