© 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. 20-GEMMASCOPE-RES-16K
    11. 9079
    Prev
    Next
    INDEX
    Explanations

    statements related to obedience and compliance with authority figures

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

    Following instructions or directions

    np_acts-logits-general · gemini-2.0-flash

    obeying orders and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.62
    ArrowToggle
    -0.62
     ostavi
    -0.49
    Datuak
    -0.49
    FilterChain
    -0.47
    ALITY
    -0.47
    ⓘ
    -0.47
     useSelector
    -0.46
    المكان
    -0.46
    évaluateur
    -0.46
    POSITIVE LOGITS
     instructions
    2.51
     instruction
    2.19
     Instructions
    2.05
     directive
    2.02
     instructed
    2.00
    instructions
    1.99
     directives
    1.98
     instructs
    1.96
     instruct
    1.93
    Instructions
    1.89
    Activations Density 0.439%

    No Known Activations