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. 1636
    Prev
    Next
    INDEX
    Explanations

    references to options and choices in a programming or technical context

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

    Tokens related to choices or settings

    np_acts-logits-general · gemini-2.0-flash

    option or options

    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
    writeField
    -0.67
    CrossRef
    -0.58
     bezeichneter
    -0.56
    signable
    -0.53
    انيف
    -0.53
    Notae
    -0.52
    뀔
    -0.50
    xDB
    -0.50
    rawQuery
    -0.50
    İstinadlar
    -0.49
    POSITIVE LOGITS
     Options
    1.33
     options
    1.28
     OPTION
    1.16
    options
    1.14
     option
    1.10
     OPTIONS
    1.05
     Choices
    1.03
     Option
    1.02
    Options
    0.99
    OPTION
    0.99
    Activations Density 0.210%

    No Known Activations