© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1201
    Prev
    Next
    INDEX
    Explanations

    references to reading or sharing reading-related experiences

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

    figures or schemes

    np_acts-logits-general · gemini-2.0-flash

    recommendations and links

    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
    AccessorTable
    -0.57
    AntiForgeryToken
    -0.56
    transQ
    -0.54
    %</
    -0.50
    الدراسه
    -0.48
     infinitive
    -0.46
    Uninitialized
    -0.46
    wohner
    -0.45
    Бахар
    -0.45
     secco
    -0.44
    POSITIVE LOGITS
     segnal
    0.77
     featured
    0.75
     listing
    0.71
     recommendation
    0.69
    紹介
    0.68
     @"/
    0.68
     Mention
    0.68
     trouva
    0.66
     links
    0.66
     recommending
    0.65
    Activations Density 0.505%

    No Known Activations