© 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. 9810
    Prev
    Next
    INDEX
    Explanations

    details about sports events and player statistics, particularly focusing on starts and milestones in leagues

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    occurrence of events

    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
    WriteLiteral
    -0.54
     imageNamed
    -0.52
     getRule
    -0.49
    økt
    -0.49
    ilor
    -0.47
    luence
    -0.45
    zsche
    -0.45
    Especially
    -0.45
     Selva
    -0.44
    EnableWeb
    -0.43
    POSITIVE LOGITS
     occurred
    0.98
     occurs
    0.85
    occurs
    0.80
     occur
    0.78
    occur
    0.77
     ocurrió
    0.73
    Occurs
    0.72
    Personendaten
    0.72
     occured
    0.72
     Occur
    0.71
    Activations Density 0.345%

    No Known Activations