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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 400
    Prev
    Next
    INDEX
    Explanations

    data and information related to statistics and governance structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.39
    ORAGE
    -0.34
    Życiorys
    -0.32
     ORDIN
    -0.32
     gustado
    -0.32
    ğine
    -0.31
     géné
    -0.31
     gọn
    -0.30
    ListItemIcon
    -0.30
     communiquez
    -0.30
    POSITIVE LOGITS
     nationwide
    0.87
     provinces
    0.78
     regions
    0.78
     counties
    0.71
     cities
    0.70
     Provinces
    0.68
     Nationwide
    0.68
    各地
    0.67
    regions
    0.67
     Regions
    0.65
    Activations Density 0.535%

    No Known Activations