© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10322
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to customer service quality and hospitality

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

    Positive or negative service/behavior feedback

    np_acts-logits-general · gemini-2.0-flash

    service demeanor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     équilibre
    -0.44
    (!__
    -0.43
     bezeichneter
    -0.42
     rahasia
    -0.42
     mécanisme
    -0.39
     EconPapers
    -0.38
     équilibr
    -0.38
     goederen
    -0.37
     autorité
    -0.37
     skolen
    -0.37
    POSITIVE LOGITS
     courteous
    0.66
     receptionist
    0.65
    polite
    0.62
     welcoming
    0.61
     friendliness
    0.60
    Greeting
    0.59
     concierge
    0.58
     polite
    0.57
     smile
    0.57
     Greet
    0.56
    Activations Density 0.198%

    No Known Activations