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. 15668
    Prev
    Next
    INDEX
    Explanations

    references to birthdays and birthday celebrations

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

    birthdays

    np_acts-logits-general · gemini-2.0-flash

    birthday, birthday party

    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
    évaluateur
    -0.58
     <>",
    -0.53
    enumii
    -0.50
    EnumMember
    -0.44
     Paglinawan
    -0.42
    styleType
    -0.42
    ROIT
    -0.40
    "]();
    -0.39
    ClientRect
    -0.38
    ContentAsync
    -0.37
    POSITIVE LOGITS
     birthday
    2.13
     Birthday
    1.84
    Birthday
    1.73
    birthday
    1.70
     birthdays
    1.60
     BIRTHDAY
    1.55
     Geburtstag
    1.55
     cumpleaños
    1.38
    🎂
    1.34
    生日
    1.32
    Activations Density 0.049%

    No Known Activations