© 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. 187
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and communities in Boston

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

    Locations in Massachusetts

    np_acts-logits-general · gemini-2.0-flash

    Boston, Massachusetts, Harvard, cities

    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
    ंदीखरीदारी
    -0.66
    ">//
    -0.58
     Montoya
    -0.57
    Kaieteur
    -0.55
     âmes
    -0.52
    jooq
    -0.52
     endwhile
    -0.51
     Schmitz
    -0.51
     hábiles
    -0.50
     jScrollPane
    -0.49
    POSITIVE LOGITS
     Massachusetts
    1.43
    Massachusetts
    1.26
     Boston
    1.25
    Boston
    1.08
     Mass
    1.05
    achusetts
    1.03
     MASSACHUSETTS
    1.03
     boston
    1.01
    BOSTON
    0.99
     Harvard
    0.98
    Activations Density 0.330%

    No Known Activations