© 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. 5388
    Prev
    Next
    INDEX
    Explanations

    phrases related to political structures and power dynamics

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

    Entities, sectors, or groups in society

    np_acts-logits-general · gemini-2.0-flash

    organized sectors

    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
    IsContent
    -0.52
     isInitialized
    -0.49
     Мексичка
    -0.47
     []:
    -0.47
    BASEPATH
    -0.46
    ról
    -0.46
    ResumeLayout
    -0.44
    Viited
    -0.43
    Примечания
    -0.41
    sidemargin
    -0.41
    POSITIVE LOGITS
     NGOs
    1.20
     academia
    1.04
     private
    0.98
     universities
    0.95
     churches
    0.91
     unions
    0.90
     civil
    0.90
     NGO
    0.87
     businesses
    0.86
     industries
    0.84
    Activations Density 0.342%

    No Known Activations