© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12051
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to authority and obedience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Not in Any Lists

    No Comments

    Negative Logits
     zwią
    -0.41
     développ
    -0.38
    équilibre
    -0.37
    évaluateur
    -0.36
     Entwicklungs
    -0.36
     parceria
    -0.35
     moneda
    -0.35
    Ehrungen
    -0.35
     recuperação
    -0.34
     desarrol
    -0.33
    POSITIVE LOGITS
     instructions
    1.16
    instructions
    1.03
     orders
    1.01
     Instructions
    1.00
     instruction
    0.94
     instructed
    0.93
     INSTRUCTIONS
    0.91
     commands
    0.91
     instructs
    0.90
     directives
    0.89
    Activations Density 0.224%

    No Known Activations