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. 10738
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions related to numbers and mathematical representations

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

    Numbers and math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical equations and identifiers

    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
     DbType
    -0.70
    ◗
    -0.68
     ذات
    -0.63
    CAPTION
    -0.63
    Портал
    -0.60
    towa
    -0.60
    zkopf
    -0.59
    WriteAttribute
    -0.59
     sot
    -0.58
    oci
    -0.57
    POSITIVE LOGITS
     myſelf
    0.70
     stamens
    0.67
     dieß
    0.63
    ⁄
    0.62
     itſelf
    0.61
     bogotá
    0.61
    ViewFeatures
    0.61
     Lilli
    0.60
    SKIN
    0.60
     tws
    0.60
    Activations Density 0.148%

    No Known Activations