© 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. 4-GEMMASCOPE-RES-16K
    11. 9742
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal actions as well as the term "act"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marconi
    -0.98
    ایج
    -0.89
    তথ্যসূত্র
    -0.86
     Brewster
    -0.85
    CloseOperation
    -0.83
     Euph
    -0.83
    RenderAtEndOf
    -0.82
     Marlborough
    -0.80
     sterili
    -0.79
    sonian
    -0.79
    POSITIVE LOGITS
     act
    2.83
     Act
    2.59
     acts
    2.56
     Acts
    2.32
    Act
    2.30
     ACT
    2.25
    act
    2.22
     acted
    2.08
    Acts
    2.01
    ACT
    1.90
    Activations Density 0.054%

    No Known Activations