© 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. 8404
    Prev
    Next
    INDEX
    Explanations

    references to inner and outer structures or concepts, particularly in a scientific or medical context

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

    "inner" followed by a comma or noun

    np_acts-logits-general · gemini-2.0-flash

    inner structures or components

    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
    ︎
    -0.70
     يتيمه
    -0.67
     الحره
    -0.66
    abetes
    -0.65
    calypse
    -0.65
     referenties
    -0.64
    wachsenen
    -0.63
    oredCriteria
    -0.63
     Wiktionnaire
    -0.63
    parsedMessage
    -0.62
    POSITIVE LOGITS
    most
    0.75
     most
    0.69
    MOST
    0.68
     layer
    0.61
     MOST
    0.59
    Most
    0.58
     workings
    0.57
     layers
    0.56
     san
    0.55
     Most
    0.55
    Activations Density 0.070%

    No Known Activations