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. 13912
    Prev
    Next
    INDEX
    Explanations

    terms related to deadlines and effective dates in legal or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tagHelperRunner
    -0.64
    modelBuilder
    -0.56
     AssemblyTitle
    -0.51
    érience
    -0.50
    exitRule
    -0.49
    KommentareTeilen
    -0.49
    HomeAsUp
    -0.48
    BorderFactory
    -0.48
    bidi
    -0.47
     onCreateView
    -0.46
    POSITIVE LOGITS
     date
    2.79
     dates
    2.57
     Date
    2.21
    date
    2.16
     DATE
    2.16
     Dates
    2.16
    dates
    2.04
    Date
    2.00
     DATES
    1.99
    DATE
    1.93
    Activations Density 0.419%

    No Known Activations