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. 20-GEMMASCOPE-RES-16K
    6. 11057
    Prev
    Next
    INDEX
    Explanations

    requests for donations and contributions

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

    Requests for donations or support

    np_acts-logits-general · gemini-2.0-flash

    soliciting donations and contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.88
    FieldBuilder
    -0.77
    contentLoaded
    -0.77
    aarrggbb
    -0.73
    ContentAsync
    -0.72
    WithIOException
    -0.72
     فريبيس
    -0.69
     defaultstate
    -0.68
    ArgumentParser
    -0.67
     Vikipedi
    -0.61
    POSITIVE LOGITS
     donations
    1.99
     donate
    1.94
     donation
    1.94
     donating
    1.69
     contributions
    1.64
     donated
    1.63
     Donations
    1.63
     Donation
    1.58
     contribution
    1.58
    Donations
    1.54
    Activations Density 0.154%

    No Known Activations