© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6867
    Prev
    Next
    INDEX
    Explanations

    actions related to communication and interactions within a structured environment, particularly involving authority and consequences

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

    Action after a time-related word

    np_acts-logits-general · gemini-2.0-flash

    arrangements and preparations

    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
    出版年
    -0.68
    脚注の使い方
    -0.66
     AppColors
    -0.64
    expandindo
    -0.60
     Мексичка
    -0.60
    oflavin
    -0.59
     Vikipedi
    -0.59
    IVEREF
    -0.59
    MMV
    -0.58
     experiencing
    -0.57
    POSITIVE LOGITS
     arrange
    1.01
     contacted
    0.94
     preparations
    0.89
     arranged
    0.89
     Preparations
    0.85
     contacting
    0.85
    Prepar
    0.83
     arrangements
    0.82
    Arrange
    0.82
     arranging
    0.82
    Activations Density 0.467%

    No Known Activations