© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11452
    Prev
    Next
    INDEX
    Explanations

    the presence of specific control characters or formatting indicators in the text

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

    Code, programming languages, or math

    np_acts-logits-general · gemini-2.0-flash

    Latin and code fragments

    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
    findpost
    -0.99
     kasarigan
    -0.92
    GraphicsUnit
    -0.92
     nahilalakip
    -0.89
    
    -0.86
    IBOutlet
    -0.82
     estimés
    -0.82
    Hauptartikel
    -0.78
    ″]
    -0.77
     فريبيس
    -0.75
    POSITIVE LOGITS
    ie
    0.55
     ejus
    0.53
     quæ
    0.50
    teen
    0.47
    возможно
    0.45
     Enfin
    0.45
    versy
    0.44
    除此之外
    0.44
     ECC
    0.44
    ঞ
    0.43
    Activations Density 0.239%

    No Known Activations