© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    elements related to dining experiences and etiquette in restaurants

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

    sitting or seating arrangements

    np_acts-logits-general · gemini-2.0-flash

    sitting or seating arrangements

    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
     Italijanski
    -0.59
    umman
    -0.56
    ukone
    -0.55
    SequentialGroup
    -0.53
     raisonnable
    -0.51
    adə
    -0.51
    ronomy
    -0.50
     indietro
    -0.50
     excès
    -0.49
     inflation
    -0.49
    POSITIVE LOGITS
     seating
    1.03
     Seating
    0.84
     seats
    0.81
     seated
    0.79
     sitting
    0.76
     seat
    0.72
     duduk
    0.71
     clientele
    0.70
     sit
    0.70
     benches
    0.67
    Activations Density 0.139%

    No Known Activations