© 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. 31-GEMMASCOPE-RES-16K
    11. 8790
    Prev
    Next
    INDEX
    Explanations

    categories or classifications of places

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

    text describing qualities and attractions of cities and travel destinations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Šaltiniai
    -0.42
     Detal
    -0.41
     virš
    -0.40
     preghi
    -0.39
     Détails
    -0.38
     للمعارف
    -0.37
    Referensi
    -0.37
     juos
    -0.37
     dupla
    -0.36
     Kelurahan
    -0.36
    POSITIVE LOGITS
     population
    0.83
     abundant
    0.75
     festivals
    0.73
     culture
    0.71
     beaches
    0.71
     nightlife
    0.71
     abundance
    0.70
     climate
    0.70
    人口
    0.70
     skyscrapers
    0.68
    Activations Density 0.483%

    No Known Activations