© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2753
    Prev
    Next
    INDEX
    Explanations

    terms related to obedience and manipulation in a hierarchical context

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

    Obedience, submission, and subservience

    np_acts-logits-general · gemini-2.0-flash

    willingly submits or obeys

    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
     demografica
    -0.61
    Хьажоргаш
    -0.54
     стаття
    -0.53
    mingen
    -0.52
     AssemblyTitle
    -0.50
     nonatomic
    -0.49
     quinn
    -0.49
    RICH
    -0.47
     Afford
    -0.47
    منابع
    -0.47
    POSITIVE LOGITS
     obedience
    1.64
     obedient
    1.62
     subserv
    1.57
     submission
    1.46
     obey
    1.45
     obeys
    1.40
     submissive
    1.40
     obeying
    1.34
     Obedience
    1.32
     obé
    1.28
    Activations Density 0.520%

    No Known Activations