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. 2886
    Prev
    Next
    INDEX
    Explanations

    details related to professional athletes' career histories

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

    Categories of nationalities and professions

    np_acts-logits-general · gemini-2.0-flash

    nationalities and subsequent categories

    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
    !”
    -1.19
    !’
    -1.10
    ”!
    -1.01
    ,”
    -0.94
    ?”
    -0.93
    ’?
    -0.91
    …”
    -0.88
    ...”
    -0.88
    ?’
    -0.86
    !!”
    -0.86
    POSITIVE LOGITS
    ).[
    1.02
    ,[
    0.88
    .[
    0.83
    ‌است
    0.82
    ♭
    0.78
     wikipagina
    0.70
     
    0.68
     tuttavia
    0.68
     subsequently
    0.68
     posteriormente
    0.67
    Activations Density 2.545%

    No Known Activations