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. 16-GEMMASCOPE-RES-16K
    6. 12562
    Prev
    Next
    INDEX
    Explanations

    references to academic publishers and their associated publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Publisher names (e.g., Springer, Wiley, Birkhäuser)

    np_acts-logits-general · gemini-2.0-flash

    academic publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -0.49
     Katzen
    -0.47
    derry
    -0.45
     goû
    -0.45
    rektur
    -0.44
     Troubleshooting
    -0.43
    rač
    -0.43
     Disqus
    -0.43
     diffé
    -0.43
    suz
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.88
    CloseOperation
    0.84
     Roskov
    0.77
     Савезне
    0.75
    ंदीखरीदारी
    0.74
    hoeddwyd
    0.72
    цездатний
    0.71
    出版年
    0.69
    Personensuche
    0.68
    AsUp
    0.66
    Activations Density 0.196%

    No Known Activations