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. 21-GEMMASCOPE-RES-16K
    6. 6903
    Prev
    Next
    INDEX
    Explanations

    specialized terms or phrases related to finance and economic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.58
    __(/*!
    -0.54
    UnsafeEnabled
    -0.54
     randomised
    -0.54
     بيها
    -0.52
    AddHtmlAttribute
    -0.51
    borderSide
    -0.50
    .~(\
    -0.47
     disponibilités
    -0.46
    annica
    -0.45
    POSITIVE LOGITS
    KommentareTeilen
    0.80
    onViewCreated
    0.71
    fillType
    0.67
    parsedMessage
    0.66
    GraphicsUnit
    0.64
    ThemeOverlay
    0.61
    ganu
    0.60
    ftagPool
    0.58
    yntaxException
    0.58
     rhestr
    0.58
    Activations Density 1.320%

    No Known Activations