Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1622
    Prev
    Next
    INDEX
    Explanations

    strings related to month and date representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.68
    GOTREF
    -0.60
    imenta
    -0.59
    MENAFN
    -0.54
    QMetaType
    -0.54
    FileDescriptor
    -0.53
    énario
    -0.52
    AntiForgeryToken
    -0.52
    UnusedPrivate
    -0.51
    CreateMap
    -0.50
    POSITIVE LOGITS
     calendar
    0.78
    Calendar
    0.77
     Calendar
    0.72
     year
    0.72
     month
    0.71
     seasonal
    0.70
    calendar
    0.70
     seasonally
    0.70
     calendario
    0.68
     Month
    0.62
    Activations Density 0.354%

    No Known Activations