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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14597
    Prev
    Next
    INDEX
    Explanations

    references to months and dates in a calendar format

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

    Months of the year (including misspellings)

    np_acts-logits-general · gemini-2.0-flash

    months of the year

    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
     StatefulWidget
    -0.49
    дится
    -0.45
    twimg
    -0.45
    ɜ
    -0.43
    awat
    -0.43
    راط
    -0.42
     ويكيميديا
    -0.41
    onDelete
    -0.41
     yıll
    -0.41
     образ
    -0.40
    POSITIVE LOGITS
     September
    1.26
     October
    1.26
     August
    1.24
     February
    1.23
     July
    1.22
     November
    1.22
     January
    1.21
     June
    1.21
     April
    1.20
     December
    1.19
    Activations Density 0.219%

    No Known Activations