© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7027
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and obedience

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

    Courtesy titles (Sir, Your Honor, Lady)

    np_acts-logits-general · gemini-2.0-flash

    formal address titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.74
     Yeah
    -0.67
    Yeah
    -0.66
     Yay
    -0.63
     Everybody
    -0.59
    viewDidLoad
    -0.59
    Yay
    -0.59
    Guys
    -0.58
     rainbows
    -0.57
     GONNA
    -0.56
    POSITIVE LOGITS
     sir
    1.34
     Sir
    1.16
    Sir
    1.08
    sir
    0.98
     dear
    0.95
     SIR
    0.94
     Mr
    0.84
     Herr
    0.83
    SIR
    0.82
    dear
    0.80
    Activations Density 0.190%

    No Known Activations