© 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. 7996
    Prev
    Next
    INDEX
    Explanations

    references to music and related entities

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

    "the" preceding a place or organization

    np_acts-logits-general · gemini-2.0-flash

    institutions 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
    Collegamenti
    -0.62
    ztal
    -0.55
    WithMany
    -0.54
    舺
    -0.52
    
    -0.51
    neapolis
    -0.50
    Jegyzetek
    -0.49
     regra
    -0.48
     &___
    -0.48
    zeiger
    -0.48
    POSITIVE LOGITS
     facility
    1.19
     venue
    0.96
     institution
    0.92
     établissement
    0.90
     premises
    0.89
     site
    0.88
    facility
    0.86
     establishment
    0.83
     station
    0.80
     houſe
    0.78
    Activations Density 0.217%

    No Known Activations