© 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. 20-GEMMASCOPE-RES-16K
    11. 3717
    Prev
    Next
    INDEX
    Explanations

    references to parental or caregiving relationships

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

    Taking someone somewhere

    np_acts-logits-general · gemini-2.0-flash

    taking them to places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndTag
    -0.47
    forName
    -0.44
    які
    -0.42
    didSet
    -0.41
     hoá
    -0.39
     geb
    -0.39
    DRIVER
    -0.39
     Coim
    -0.39
    ucket
    -0.39
     Fä
    -0.38
    POSITIVE LOGITS
     everywhere
    0.82
    CloseOperation
    0.81
     shopping
    0.76
    everywhere
    0.76
     partout
    0.76
     Everywhere
    0.68
    Tembelea
    0.68
    expandindo
    0.65
     places
    0.64
    toBeDefined
    0.64
    Activations Density 0.118%

    No Known Activations