© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8397
    Prev
    Next
    INDEX
    Explanations

    mentions of "New York" and "Times."

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

    NY or York

    np_acts-logits-general · gemini-2.0-flash

    NY Times and NY entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bodies
    -0.88
     Bodies
    -0.76
     cuerpos
    -0.74
     ciała
    -0.71
    Bodies
    -0.65
    bodies
    -0.64
     tubuh
    -0.63
     cuerpo
    -0.62
     body
    -0.60
     Körper
    -0.57
    POSITIVE LOGITS
     York
    0.67
     NY
    0.65
    York
    0.63
     Ny
    0.59
     ny
    0.57
     york
    0.57
     YORK
    0.54
    YORK
    0.54
    Ny
    0.52
     City
    0.50
    Activations Density 0.071%

    No Known Activations