© 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. 22-GEMMASCOPE-RES-16K
    11. 3962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or role of various entities in contexts such as medical conditions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "are" followed by a descriptor

    np_acts-logits-general · gemini-2.0-flash

    are candidates, determinants, identified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     lèvres
    -0.87
     épaules
    -0.85
     dépens
    -0.83
     pouvoirs
    -0.78
     gouvernements
    -0.73
     vœux
    -0.72
     négociations
    -0.71
     genoux
    -0.71
     jambes
    -0.69
     églises
    -0.69
    POSITIVE LOGITS
     examples
    1.08
     ones
    0.97
     những
    0.96
     extensions
    0.94
     catalysts
    0.92
     targets
    0.92
     constants
    0.91
     exceptions
    0.90
     indicators
    0.90
     precursors
    0.89
    Activations Density 0.909%

    No Known Activations