© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8178
    Prev
    Next
    INDEX
    Explanations

    mentions of sports signings and player careers in soccer

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

    Follows specific prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    numbers and locations

    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
     MotoGP
    -0.64
     olímp
    -0.57
     Guggenheim
    -0.57
     NHL
    -0.56
    Pulitzer
    -0.55
    MIDDLEWARE
    -0.55
     végétal
    -0.54
    Sklici
    -0.53
    NYSE
    -0.52
     Eurovision
    -0.52
    POSITIVE LOGITS
     cherchés
    0.78
    ThroughAttribute
    0.73
     насељу
    0.72
     betweenstory
    0.69
     Baillargeon
    0.65
    TypedDataSet
    0.60
     EconPapers
    0.59
     resourceCulture
    0.59
    aderie
    0.58
     المعرف
    0.58
    Activations Density 0.211%

    No Known Activations