© 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. 507
    Prev
    Next
    INDEX
    Explanations

    system-related keywords and error handling terms

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

    Code snippets, file paths, or MIME types

    np_acts-logits-general · gemini-2.0-flash

    sharing with email/whatsapp

    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
    AntiForgeryToken
    -0.55
    Karakteristik
    -0.55
     сті
    -0.51
    centerY
    -0.50
     walls
    -0.50
     Walls
    -0.49
     esthétique
    -0.48
     PropertyChanged
    -0.48
     கூ
    -0.47
    Walls
    -0.47
    POSITIVE LOGITS
     незавершена
    0.80
     חיצוניים
    0.76
    Personendaten
    0.70
     Conſ
    0.63
     whoſe
    0.63
    TagMode
    0.62
     Efq
    0.62
     Reſ
    0.60
     Monfieur
    0.60
     bezeichneter
    0.59
    Activations Density 0.277%

    No Known Activations