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. 3-GEMMASCOPE-RES-16K
    6. 11033
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.11
     nahilalakip
    -1.07
     يتيمه
    -1.02
    IonicModule
    -1.01
    rungsseite
    -0.96
    KommentareTeilen
    -0.95
     ویکی‌پدیای
    -0.91
    webElementXpaths
    -0.87
     MessageBoxIcon
    -0.86
     NUKAT
    -0.85
    POSITIVE LOGITS
    Def
    2.85
     Def
    2.77
     def
    2.77
    def
    2.48
    DEF
    2.29
     DEF
    2.26
    Defs
    1.67
     déf
    1.57
    defs
    1.47
     defi
    1.47
    Activations Density 0.109%

    No Known Activations