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. 25-GEMMASCOPE-RES-16K
    6. 10247
    Prev
    Next
    INDEX
    Explanations

    phrases related to forex trading and community support for traders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Altri
    -0.56
     Egli
    -0.52
     Forse
    -0.51
     Quindi
    -0.51
     alkalinity
    -0.51
     Tutte
    -0.50
     Ciò
    -0.49
     embank
    -0.49
     follicular
    -0.47
     Queste
    -0.47
    POSITIVE LOGITS
     dan
    0.58
     yang
    0.51
     dengan
    0.51
     untuk
    0.48
     ini
    0.48
     yaitu
    0.48
     adalah
    0.46
     serta
    0.46
     dari
    0.45
     terhadap
    0.45
    Activations Density 0.114%

    No Known Activations