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. 10988
    Prev
    Next
    INDEX
    Explanations

    phrases expressing knowledge and inquiry

    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
    ใหญ่
    -0.48
    }^{-}
    -0.46
    ^{-}\
    -0.46
    ]^{-
    -0.46
    ^{-}
    -0.45
    酒屋
    -0.44
    getBoard
    -0.44
    ่อย
    -0.43
     مرت
    -0.42
    Filmografie
    -0.42
    POSITIVE LOGITS
    IsContent
    1.04
    tagHelperRunner
    1.01
     NSCoder
    0.98
    webElementGuid
    0.98
    KommentareTeilen
    0.97
     AppColors
    0.89
     تضيفلها
    0.87
    AddTagHelper
    0.84
    IndentedString
    0.81
    الإنجليزية
    0.81
    Activations Density 0.160%

    No Known Activations