© 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. 18-GEMMASCOPE-RES-16K
    11. 1894
    Prev
    Next
    INDEX
    Explanations

    sports tournament formats and bracket-related information

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

    Tokens within parenthesis

    np_acts-logits-general · gemini-2.0-flash

    sports rankings / seeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Atsauces
    -0.61
    Бележки
    -0.60
     competitive
    -0.55
    TagHelper
    -0.54
     near
    -0.54
    "}")
    -0.52
     concorso
    -0.52
    Completo
    -0.51
    sphase
    -0.50
    arwal
    -0.50
    POSITIVE LOGITS
     seeded
    0.85
     seed
    0.81
    seed
    0.74
     seeding
    0.72
     seeds
    0.71
     Seed
    0.68
    Seed
    0.68
    seeded
    0.67
     Seeds
    0.59
    seeds
    0.58
    Activations Density 0.081%

    No Known Activations