© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    instances of special tokens or markers in a document

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

    Text following the letter "Q" (often questions)

    np_acts-logits-general · gemini-2.0-flash

    expiration, at, Bur, Q, Vitamin, expiration, at, of

    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
     nakalista
    -0.66
    DeleteBehavior
    -0.60
    ässä
    -0.57
     ivelany
    -0.55
     quí
    -0.55
    centralwidget
    -0.53
    erez
    -0.53
    \{\\
    -0.52
     BitmapFactory
    -0.52
    ysacchar
    -0.50
    POSITIVE LOGITS
    TagMode
    0.81
    ftagPool
    0.74
    mem
    0.57
     mem
    0.57
     BoxDecoration
    0.53
     typelib
    0.51
     floor
    0.51
     invitar
    0.51
     createState
    0.49
     useState
    0.49
    Activations Density 0.026%

    No Known Activations