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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 690
    Prev
    Next
    INDEX
    Explanations

    descriptions of rude behavior and character traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.74
    GEBURTS
    -0.71
    parsedMessage
    -0.66
    Personendaten
    -0.60
    出版年
    -0.60
    DataAnnotations
    -0.60
    webElementXpaths
    -0.58
     kapture
    -0.57
     tartalomajánló
    -0.57
    InputBorder
    -0.56
    POSITIVE LOGITS
     arrogant
    1.41
     arrogance
    1.27
     cocky
    1.09
     haughty
    1.08
     arrog
    1.06
     rude
    1.02
     ego
    1.01
     attitude
    1.00
     arro
    0.93
     disrespectful
    0.90
    Activations Density 0.487%

    No Known Activations