© 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. 11847
    Prev
    Next
    INDEX
    Explanations

    elements related to cooking and baking processes

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

    Code, numbers, and symbols

    np_acts-logits-general · gemini-2.0-flash

    STATUS(x)

    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
     cref
    -0.45
    enschap
    -0.45
     незавершена
    -0.43
     فريبيس
    -0.42
     AUSSI
    -0.42
    rubin
    -0.41
    openqa
    -0.41
     jaunes
    -0.40
    phrag
    -0.40
    ItemType
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.89
    localctx
    0.86
     Serve
    0.77
    writeFieldEnd
    0.73
    Serve
    0.70
    TabIndex
    0.68
    corer
    0.66
     serving
    0.66
     serve
    0.65
     servire
    0.63
    Activations Density 0.116%

    No Known Activations