© 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. 8609
    Prev
    Next
    INDEX
    Explanations

    the name "Ara" in various contexts and forms

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

    Starts with "Ara" or "Dra" and is not a common English word

    np_acts-logits-general · gemini-2.0-flash

    Ar... words

    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
    g
    -0.63
    gill
    -0.62
    н
    -0.57
    gab
    -0.53
    encies
    -0.53
    gea
    -0.53
    m
    -0.52
    gus
    -0.51
    gó
    -0.51
    sav
    -0.51
    POSITIVE LOGITS
     Exacts
    0.78
    Lähteet
    0.77
     nahilalakip
    0.75
    évaluateur
    0.69
    GEBURTSDATUM
    0.66
    XmlAccessType
    0.66
    IsContent
    0.65
    PMailer
    0.65
     NSCoder
    0.65
    principalColumn
    0.64
    Activations Density 0.186%

    No Known Activations