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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5094
    Prev
    Next
    INDEX
    Explanations

    specific breakfast items and their qualities, especially in the context of cultural food experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Tembelea
    -0.49
     fédé
    -0.44
     froide
    -0.38
     دام
    -0.38
    PropertyChanging
    -0.38
     feroit
    -0.37
    msgTypes
    -0.36
     nahilalakip
    -0.36
    ginate
    -0.35
     يتيمه
    -0.35
    POSITIVE LOGITS
    ItemBackground
    0.49
    brought
    0.46
     חיצוניים
    0.43
    postIndex
    0.43
     insuffisamment
    0.41
    glected
    0.40
    absent
    0.39
     jiwa
    0.39
     brought
    0.38
    Становништво
    0.38
    Activations Density 0.622%

    No Known Activations