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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2081
    Prev
    Next
    INDEX
    Explanations

    dates, particularly those formatted with the month, day, and year

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Jan" or "January"

    np_acts-logits-general · gemini-2.0-flash

    Jan or January names and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lokales
    -0.52
     server
    -0.43
     Ragh
    -0.43
    они
    -0.43
    UrlEncoded
    -0.43
    angg
    -0.43
     Combien
    -0.42
    Reina
    -0.41
    retmen
    -0.41
     tık
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.99
    +#+#
    0.96
     JAN
    0.87
    JAN
    0.80
    Jan
    0.79
     Jan
    0.78
     MenuView
    0.77
    fjspx
    0.75
     JANUARY
    0.74
     jan
    0.74
    Activations Density 0.079%

    No Known Activations