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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16123
    Prev
    Next
    INDEX
    Explanations

    month names and dates

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

    Names of months

    np_acts-logits-general · gemini-2.0-flash

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.68
    RenderAtEndOf
    -0.58
    Personensuche
    -0.55
     propOrder
    -0.54
    Obrázky
    -0.53
    elemField
    -0.48
    balleur
    -0.45
     useContext
    -0.43
     localObject
    -0.43
    SharedDtor
    -0.42
    POSITIVE LOGITS
     måned
    0.75
     меся
    0.68
     month
    0.60
     mensual
    0.55
     Month
    0.54
    Month
    0.54
    teenth
    0.52
     месяца
    0.51
     monthly
    0.50
     ayı
    0.50
    Activations Density 0.139%

    No Known Activations