Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1484
    Prev
    Next
    INDEX
    Explanations

    prominent individuals and their contributions or roles in specific contexts

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

    Preceding "was" or "who" describing a person

    np_acts-logits-general · gemini-2.0-flash

    person's description following "was" or relative clause after "who"

    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
     derzeit
    -0.70
     momentan
    -0.67
     currently
    -0.67
     recent
    -0.67
     newest
    -0.65
     presently
    -0.62
     récentes
    -0.60
     latest
    -0.59
     ويكيميديا
    -0.58
     recently
    -0.58
    POSITIVE LOGITS
     died
    0.87
     posthum
    0.85
    famous
    0.83
     famous
    0.79
     lived
    0.79
     legendary
    0.78
     pioneer
    0.77
     influential
    0.77
    legendary
    0.75
     pioneering
    0.74
    Activations Density 0.571%

    No Known Activations