© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements in recipes

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

    Units of cooking measurements

    np_acts-logits-general · gemini-2.0-flash

    units and ingredients

    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
     república
    -0.61
    InvalidProtocol
    -0.58
    HashCode
    -0.54
    popd
    -0.53
    !("{
    -0.52
    \}\\
    -0.52
    LookAnd
    -0.51
     atend
    -0.50
     frukt
    -0.47
     فريبيس
    -0.46
    POSITIVE LOGITS
     disambiguazione
    0.71
    帖最后由
    0.60
    orsese
    0.59
     jsPsych
    0.58
    PerPage
    0.56
    BrowserModule
    0.55
    ctrica
    0.55
    djangoproject
    0.55
    Personendaten
    0.54
    NUMX
    0.54
    Activations Density 0.096%

    No Known Activations