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. 11-GEMMASCOPE-RES-16K
    6. 5960
    Prev
    Next
    INDEX
    Explanations

    inquiries about specific items or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tripod
    -0.63
    PLEX
    -0.56
    FXMLLoader
    -0.55
    UMBUS
    -0.54
     raising
    -0.54
     tripod
    -0.54
    emus
    -0.53
     berpikir
    -0.53
     зай
    -0.51
     Zeug
    -0.51
    POSITIVE LOGITS
     незавершена
    1.08
     Welche
    0.96
     hangi
    0.95
     Which
    0.94
     welk
    0.92
    hichever
    0.90
     Quais
    0.89
    Which
    0.87
     Какой
    0.85
    InjectMocks
    0.83
    Activations Density 0.109%

    No Known Activations