© 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. 16-GEMMASCOPE-RES-16K
    11. 3509
    Prev
    Next
    INDEX
    Explanations

    references to New York and its various contexts, including locations, institutions, and media entities

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

    New York

    np_acts-logits-general · gemini-2.0-flash

    New York City, NY, NYC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.66
     Walkover
    -0.65
     ActionListener
    -0.65
    期刊论文
    -0.63
    JsonObject
    -0.61
     Ena
    -0.60
     manuales
    -0.60
     Hoon
    -0.60
    Deadly
    -0.60
    ardis
    -0.59
    POSITIVE LOGITS
     NY
    1.47
     NYC
    1.25
     York
    1.25
     Knicks
    1.16
    NY
    1.14
    York
    1.12
    NYC
    1.11
     Yorkers
    1.11
    nyc
    1.08
     Mets
    1.05
    Activations Density 0.220%

    No Known Activations