© 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. 975
    Prev
    Next
    INDEX
    Explanations

    instances of words related to searching for specific items or information

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

    or tokens following percentages

    np_acts-logits-general · gemini-2.0-flash

    menstrual flow and cycle

    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
     champagne
    -0.58
     ddelweddau
    -0.52
     Champagne
    -0.51
    dorff
    -0.50
     Citrus
    -0.48
    riwal
    -0.47
    idjan
    -0.46
    Citrus
    -0.46
     Conch
    -0.46
     odb
    -0.46
    POSITIVE LOGITS
    Hentet
    0.87
    SequentialGroup
    0.80
    AnchorStyles
    0.74
     propOrder
    0.69
     ModelExpression
    0.68
    TemporalType
    0.66
    Lynch
    0.63
    HomeAsUpEnabled
    0.63
    رشف
    0.61
    resizingMask
    0.61
    Activations Density 0.064%

    No Known Activations