© 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. 3690
    Prev
    Next
    INDEX
    Explanations

    phrases related to navigating directions and movement

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

    Follows prepositions "out" or "up."

    np_acts-logits-general · gemini-2.0-flash

    up out down

    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
    him
    -0.56
     οποία
    -0.54
     zich
    -0.53
    之
    -0.52
    álních
    -0.52
    ally
    -0.52
    nya
    -0.51
     brancas
    -0.48
    ist
    -0.48
     lui
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.97
     AssemblyCulture
    0.96
     estekak
    0.94
     >=",
    0.91
    pexpr
    0.87
    ftagPool
    0.85
     NSCoder
    0.83
     Biôgrafia
    0.83
    AsUp
    0.81
    Diweddarwch
    0.80
    Activations Density 0.255%

    No Known Activations