Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10871
    Prev
    Next
    INDEX
    Explanations

    queries related to people's knowledge and familiarity with various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gawai
    -0.54
     démocr
    -0.47
     grantee
    -0.45
     Dimen
    -0.44
    haf
    -0.44
     suprême
    -0.44
     combineReducers
    -0.44
    fromCharCode
    -0.43
     cruzado
    -0.43
     affichés
    -0.43
    POSITIVE LOGITS
    verwijspagina
    0.83
     חיצוניים
    0.75
     Roskov
    0.74
    Hauptartikel
    0.73
    InjectAttribute
    0.69
     nahilalakip
    0.69
     surla
    0.68
     StringTokenizer
    0.68
    Carriera
    0.67
    PreferredItem
    0.65
    Activations Density 0.291%

    No Known Activations