© 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. 14728
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology related to measurements and models

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

    followed by commas or prepositions

    np_acts-logits-general · gemini-2.0-flash

    than

    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
     >=",
    -0.66
    存于互联网档案馆
    -0.61
    ImageContext
    -0.61
    SequentialGroup
    -0.58
     zamiast
    -0.57
     sumpay
    -0.57
     Junto
    -0.56
    EndGlobalSection
    -0.56
     transférez
    -0.56
     versus
    -0.55
    POSITIVE LOGITS
     does
    0.92
     counterparts
    0.88
    does
    0.83
     did
    0.81
     counterpart
    0.79
     Does
    0.76
    那样
    0.74
     pourtant
    0.69
     albeit
    0.67
    Does
    0.67
    Activations Density 0.558%

    No Known Activations