© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9360
    Prev
    Next
    INDEX
    Explanations

    terms associated with arrogance and inflated self-perception

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

    Descriptions of arrogance or superiority

    np_acts-logits-general · gemini-2.0-flash

    arrogant and arrogance

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    •list 2

    No Comments

    Negative Logits
     miniaturka
    -0.46
     edades
    -0.46
     pères
    -0.45
     bílá
    -0.44
     pungkas
    -0.43
     estaciones
    -0.43
     bendera
    -0.43
     órg
    -0.42
     peuples
    -0.41
    jangkau
    -0.41
    POSITIVE LOGITS
     arrog
    0.77
     arrogant
    0.75
     arrogance
    0.70
     cocky
    0.66
     Strut
    0.64
     strut
    0.62
     swagger
    0.59
     claim
    0.59
     ego
    0.58
     pride
    0.58
    Activations Density 0.308%

    No Known Activations