© 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. 6713
    Prev
    Next
    INDEX
    Explanations

    references to authority and decision-making within organizational contexts

    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
     placent
    -0.55
    StructEnd
    -0.53
    InvalidProtocol
    -0.51
     devenir
    -0.51
     Neuk
    -0.49
     couvert
    -0.49
     vermelhas
    -0.48
     tóxic
    -0.48
     quelcon
    -0.48
     deviennent
    -0.47
    POSITIVE LOGITS
    TagMode
    0.70
    tvguidetime
    0.63
    iastes
    0.62
     chi̍t
    0.61
    setVerticalGroup
    0.60
     више
    0.59
    참고
    0.59
     autorytatywna
    0.59
    complexContent
    0.56
     included
    0.56
    Activations Density 0.262%

    No Known Activations