© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10263
    Prev
    Next
    INDEX
    Explanations

    references to Swedish organizations and institutions

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

    proper nouns and names of people, places, and organizations.

    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
     varandra
    -0.73
     gången
    -0.72
     verksamhet
    -0.67
     vägen
    -0.67
     igång
    -0.65
     svårt
    -0.64
     möjligt
    -0.63
     ögon
    -0.63
     färg
    -0.62
     ägg
    -0.60
    POSITIVE LOGITS
     Swedish
    1.53
    Swedish
    1.41
     Sweden
    1.37
     schwed
    1.31
    Sweden
    1.27
     swedish
    1.27
     Swedes
    1.20
     Stockholm
    1.13
    瑞典
    1.13
     sweden
    1.13
    Activations Density 0.574%

    No Known Activations