© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3900
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and compliance with orders

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

    Following orders or instructions

    np_acts-logits-general · gemini-2.0-flash

    issuing and obeying orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.59
     createState
    -0.53
     Sted
    -0.50
     ostavi
    -0.49
    ⓘ
    -0.47
     indisponible
    -0.47
     Stedman
    -0.47
     Buddy
    -0.47
     Budd
    -0.46
    المكان
    -0.46
    POSITIVE LOGITS
     orders
    1.93
     command
    1.83
     commands
    1.79
    命令
    1.67
     instructions
    1.67
     Orders
    1.59
     directive
    1.58
     perintah
    1.56
     order
    1.53
    orders
    1.52
    Activations Density 0.367%

    No Known Activations