© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize perspectives or viewpoints

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

    "Point of view" or perspective

    np_acts-logits-general · gemini-2.0-flash

    point of view

    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
    曖昧さ回避
    -0.62
     متعلقه
    -0.57
     eventdata
    -0.52
    قایناق‌لار
    -0.49
    الإنجليزية
    -0.49
    Advertisement
    -0.47
    itania
    -0.46
     оригіналу
    -0.46
    тельстве
    -0.46
    IndentedString
    -0.45
    POSITIVE LOGITS
     view
    2.42
     View
    2.07
    view
    2.07
    View
    2.00
     VIEW
    1.91
     views
    1.88
    VIEW
    1.74
     Views
    1.61
    views
    1.57
     sight
    1.52
    Activations Density 0.227%

    No Known Activations