© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16202
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and notable individuals within the context of teaching or learning environments

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

    New York City

    np_acts-logits-general · gemini-2.0-flash

    New York City locations

    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
     defaultstate
    -0.87
    
    -0.79
     >=",
    -0.75
    minecraftforge
    -0.69
    ///</
    -0.68
    brainly
    -0.67
    FunctionFlags
    -0.64
    Дереккөздер
    -0.64
    IContainer
    -0.63
    Зноскі
    -0.61
    POSITIVE LOGITS
     NYC
    1.58
     Manhattan
    1.55
    NYC
    1.50
     NY
    1.47
    NY
    1.37
    Manhattan
    1.31
     NYPD
    1.31
     Bronx
    1.22
     Harlem
    1.20
     NYU
    1.19
    Activations Density 0.381%

    No Known Activations