© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 1469
    Prev
    Next
    INDEX
    Explanations

    terms and references related to various aspects of societal roles and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.61
     -
    -0.54
    ↵↵
    -0.52
     (
    -0.50
     africains
    -0.49
     compagni
    -0.48
     européens
    -0.47
     –
    -0.46
    usercontent
    -0.46
    …
    -0.46
    POSITIVE LOGITS
    Filmographie
    0.87
    thâu
    0.83
     Мексичка
    0.83
     vuitton
    0.77
    Personendaten
    0.76
    ugeot
    0.75
    
    0.75
    ՚
    0.74
    ERRA
    0.71
     Byzantine
    0.71
    Activations Density 1.570%

    No Known Activations