© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2622
    Prev
    Next
    INDEX
    Explanations

    terms related to dates and timelines in legal contexts

    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
    tagHelperRunner
    -0.55
     chi̍t
    -0.52
    tagHelper
    -0.51
    BorderFactory
    -0.50
    KommentareTeilen
    -0.46
    HomeAsUp
    -0.42
     виправивши
    -0.42
    <?
    -0.42
    DotNetBar
    -0.42
    JMenu
    -0.41
    POSITIVE LOGITS
     date
    3.28
     dates
    2.72
    date
    2.62
     Date
    2.58
     DATE
    2.45
    Date
    2.41
     Dates
    2.22
    DATE
    2.18
    dates
    2.14
     DATES
    2.04
    Activations Density 0.344%

    No Known Activations