© 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. 3748
    Prev
    Next
    INDEX
    Explanations

    specific keywords and phrases related to formal or legal scenarios

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

    Non-English text or code

    np_acts-logits-general · gemini-2.0-flash

    impaired, renew, ので

    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
     (
    -0.61
    における
    -0.56
     the
    -0.54
     and
    -0.51
     with
    -0.50
     but
    -0.49
     in
    -0.49
     وكانت
    -0.49
    ,
    -0.48
     from
    -0.47
    POSITIVE LOGITS
    batore
    0.94
     Italijanski
    0.94
    Portale
    0.93
    enderror
    0.93
    存于互联网档案馆
    0.91
     propOrder
    0.88
     CURIAM
    0.87
     ब्रेकडाउन
    0.86
     autorytatywna
    0.86
     EconPapers
    0.85
    Activations Density 0.267%

    No Known Activations