© 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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8806
    Prev
    Next
    INDEX
    Explanations

    detailed technical descriptions of computer system operations, hardware-level instructions, and performance evaluation processes

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    references to procedural or process-related aspects in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
    •test

    No Comments

    Negative Logits
     the
    -0.76
     it
    -0.59
     its
    -0.59
     we
    -0.52
     an
    -0.51
    Demografía
    -0.50
     his
    -0.50
     a
    -0.49
    Kilder
    -0.49
     belangrij
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.81
    ↵↵
    0.68
    ChildScrollView
    0.62
    '
    0.62
     Shakspeare
    0.61
    ↵
    0.54
    ongoose
    0.54
    iddhar
    0.54
    tonode
    0.54
    manteau
    0.52
    Activations Density 2.948%

    No Known Activations