© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5339
    Prev
    Next
    INDEX
    Explanations

    references to various types of offices and office-related roles

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

    "office" or related terms

    np_acts-logits-general · gemini-2.0-flash

    office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ésult
    -0.58
    Formazione
    -0.55
    Rüyada
    -0.54
    出版年
    -0.53
     stratégique
    -0.52
     senhora
    -0.52
     chłop
    -0.51
    Citiți
    -0.50
     alimentaires
    -0.50
     regioni
    -0.50
    POSITIVE LOGITS
    Office
    0.66
     Office
    0.66
     OFFICE
    0.61
    office
    0.60
     office
    0.57
     Offices
    0.54
    OFFICE
    0.53
     propOrder
    0.51
     offices
    0.48
    WEBPACK
    0.46
    Activations Density 0.105%

    No Known Activations