© 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. 3-GEMMASCOPE-RES-16K
    11. 7782
    Prev
    Next
    INDEX
    Explanations

    variations of the word "evacuate" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.94
    RenderAtEndOf
    -0.88
     Meksiku
    -0.80
     MainAxisSize
    -0.77
    ToBounds
    -0.76
    InputBorder
    -0.75
     }}"></
    -0.72
     Berthe
    -0.71
     Compro
    -0.69
     ofreci
    -0.68
    POSITIVE LOGITS
     ev
    2.92
    ev
    2.81
     Ev
    2.77
    Ev
    2.66
     EV
    2.19
    EV
    2.09
    evs
    1.45
     Evans
    1.33
     eviction
    1.32
     Evang
    1.31
    Activations Density 0.104%

    No Known Activations