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. 5-GEMMASCOPE-RES-16K
    6. 4774
    Prev
    Next
    INDEX
    Explanations

    references to corporate and governmental actions, particularly in relation to investigations and mergers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是非常
    -0.69
    非常的
    -0.66
     rigtig
    -0.56
    这件事情
    -0.54
     idag
    -0.53
    τύ
    -0.51
    很多的
    -0.51
    mıştır
    -0.50
     diatas
    -0.48
     mnoho
    -0.48
    POSITIVE LOGITS
     booze
    0.99
     woes
    0.97
     ujednoznacz
    0.95
     staffers
    0.94
     foes
    0.90
     pricey
    0.90
     Majefty
    0.88
     amid
    0.87
     penned
    0.87
    leſs
    0.85
    Activations Density 0.531%

    No Known Activations