© 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. 16180
    Prev
    Next
    INDEX
    Explanations

    Java import statements and data structure declarations

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

    Code or technical language

    np_acts-logits-general · gemini-2.0-flash

    technical specifications and terms

    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
    別
    -0.56
     But
    -0.50
     :
    -0.50
     de
    -0.49
     De
    -0.49
    But
    -0.48
     Don
    -0.47
     DE
    -0.47
     e
    -0.46
     but
    -0.46
    POSITIVE LOGITS
     дописавши
    0.89
     typelib
    0.85
     Theſe
    0.84
     jScrollPane
    0.84
     виправивши
    0.83
     initComponents
    0.81
     فريبيس
    0.81
    ंदीखरीदारी
    0.81
     myſelf
    0.81
     disambiguazione
    0.80
    Activations Density 0.145%

    No Known Activations