© 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. 3787
    Prev
    Next
    INDEX
    Explanations

    connections between different concepts or ideas within textual data

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

    French text, often containing "ca"

    np_acts-logits-general · gemini-2.0-flash

    "ca" followed by verbs

    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
     desiring
    -0.57
    ोंने
    -0.57
    vited
    -0.55
     disponibilités
    -0.54
    aware
    -0.53
     wishing
    -0.51
    writeFieldEnd
    -0.51
    طيع
    -0.51
     Aware
    -0.50
     fontsize
    -0.50
    POSITIVE LOGITS
     is
    0.65
    帖最后由
    0.64
     belongs
    0.64
     belong
    0.64
     αποτε
    0.60
     entail
    0.57
     comprises
    0.57
     comprise
    0.56
     represent
    0.55
     represents
    0.54
    Activations Density 0.042%

    No Known Activations