© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15194
    Prev
    Next
    INDEX
    Explanations

    specific terms related to legal and governmental contexts

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

    Prepositions or words immediately after

    np_acts-logits-general · gemini-2.0-flash

    enrollment, prior, trade, bandwidth, felt, medical, human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queen
    -0.76
     un
    -0.73
     bank
    -0.71
     ha
    -0.70
     ch
    -0.69
     pu
    -0.69
     ten
    -0.69
     net
    -0.68
     king
    -0.68
     tel
    -0.66
    POSITIVE LOGITS
     Grecs
    1.02
     Houſe
    0.97
     varandra
    0.92
     Juifs
    0.92
     Eſ
    0.87
     Reſ
    0.87
     prisonniers
    0.87
     copertura
    0.86
     Jefus
    0.85
     feroit
    0.84
    Activations Density 2.211%

    No Known Activations