© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5322
    Prev
    Next
    INDEX
    Explanations

    iterations of the word "responsible" and phrases related to accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.46
     ujednoznacz
    -0.44
     kyllä
    -0.42
    geslacht
    -0.42
     vœ
    -0.41
     zupeł
    -0.39
     uitz
    -0.38
    viewtopic
    -0.38
     libremente
    -0.35
     nytt
    -0.34
    POSITIVE LOGITS
     responsibility
    1.63
     responsible
    1.62
     Responsibility
    1.59
    responsible
    1.54
     Responsible
    1.54
    Responsible
    1.50
    Responsibility
    1.44
    responsibility
    1.43
     responsable
    1.35
     responsables
    1.21
    Activations Density 0.162%

    No Known Activations