© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58563
    Prev
    Next
    INDEX
    Explanations

    terms related to obedience and following orders

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

    obey and obedience

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CardView
    -0.42
     Partagez
    -0.42
    <#
    -0.41
    $('#
    -0.41
     recherchez
    -0.40
     assets
    -0.40
     feel
    -0.39
     Mitter
    -0.39
    وصلات
    -0.38
    AlterField
    -0.38
    POSITIVE LOGITS
     Obedience
    1.13
     obedience
    1.08
    obedience
    0.99
    obey
    0.94
     obed
    0.92
     obeyed
    0.92
     obey
    0.91
     obé
    0.90
     obedient
    0.84
    obed
    0.83
    Activations Density 0.010%

    No Known Activations