© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 89895
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to respect and recognition

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

    respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.40
     an
    -0.39
     Miao
    -0.39
    {~
    -0.38
     Milla
    -0.38
     Bayou
    -0.36
     Nia
    -0.33
    Loan
    -0.33
    нъ
    -0.32
     Liu
    -0.32
    POSITIVE LOGITS
     respect
    0.99
     Respect
    0.98
    respect
    0.98
    Respect
    0.96
     RESPECT
    0.93
     respectful
    0.91
     respected
    0.85
     respects
    0.83
     respekt
    0.82
     respek
    0.81
    Activations Density 0.016%

    No Known Activations