© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4049
    Prev
    Next
    INDEX
    Explanations

    phrases related to commands, orders, and obedience in hierarchical structures

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

    Instructions and orders

    np_acts-logits-general · gemini-2.0-flash

    commands and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    évaluateur
    -0.39
    TimeUnit
    -0.35
    tilhe
    -0.35
     Gewähr
    -0.34
    resentation
    -0.33
     sén
    -0.33
     moneda
    -0.33
     Sénat
    -0.33
     Eucharist
    -0.32
     développ
    -0.32
    POSITIVE LOGITS
     instructions
    1.07
    instructions
    0.94
     instructed
    0.92
     Instructions
    0.90
     orders
    0.88
     instruction
    0.85
     instructs
    0.85
    instru
    0.84
     INSTRUCTIONS
    0.83
     instruct
    0.81
    Activations Density 0.394%

    No Known Activations