© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7813
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture and architectural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.56
     oignons
    -0.56
    stretchr
    -0.54
    Datuak
    -0.51
     drep
    -0.50
    aarrggbb
    -0.47
     oeufs
    -0.47
    WebControls
    -0.47
    AlterField
    -0.46
    lit
    -0.44
    POSITIVE LOGITS
     extracts
    0.97
     Extracts
    0.94
     extract
    0.89
     Landscape
    0.83
     flour
    0.81
     Extract
    0.80
    SharedCtor
    0.77
     LANDSCAPE
    0.76
    Flour
    0.76
    extract
    0.75
    Activations Density 0.084%

    No Known Activations