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. 3-GEMMASCOPE-RES-16K
    6. 12799
    Prev
    Next
    INDEX
    Explanations

    the presence of various types of date representations in the text

    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
    Autoritní
    -0.97
     autorytatywna
    -0.96
    HttpPut
    -0.86
    RegistryLite
    -0.84
    AccessorTable
    -0.83
    oredCriteria
    -0.81
    ніципа
    -0.80
     vendeurs
    -0.80
     Infórmanos
    -0.79
    migrationBuilder
    -0.77
    POSITIVE LOGITS
    date
    1.26
    DATE
    1.16
    getDate
    1.11
    setDate
    1.01
    Date
    0.98
     DATE
    0.98
     getDate
    0.94
     date
    0.91
    datepicker
    0.87
    orianCalendar
    0.84
    Activations Density 0.047%

    No Known Activations