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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4336
    Prev
    Next
    INDEX
    Explanations

    references to New York City and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yelek
    -0.58
    astéro
    -0.57
    zeß
    -0.54
     citoy
    -0.54
     maș
    -0.53
     turística
    -0.53
     alimentaria
    -0.53
     creș
    -0.52
    romyalgia
    -0.51
     împre
    -0.51
    POSITIVE LOGITS
     York
    1.48
     YORK
    1.33
     york
    1.25
    York
    1.23
    york
    1.08
    YORK
    1.03
     NY
    0.88
    ニューヨーク
    0.81
    纽约
    0.81
    ヨーク
    0.73
    Activations Density 0.104%

    No Known Activations