© 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. 7856
    Prev
    Next
    INDEX
    Explanations

    references to acts or actions, particularly in a legal or formal context

    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
    ایج
    -0.83
     Marconi
    -0.81
     nahilalakip
    -0.76
    CloseOperation
    -0.75
    ColumnHeaders
    -0.74
    sonian
    -0.74
    nexpected
    -0.72
     Brewster
    -0.70
    Hentet
    -0.69
     Terraria
    -0.69
    POSITIVE LOGITS
     act
    3.37
     Act
    2.99
     acts
    2.98
    Act
    2.75
     Acts
    2.75
    act
    2.69
     ACT
    2.60
    Acts
    2.43
     ACTS
    2.31
     acted
    2.28
    Activations Density 0.059%

    No Known Activations