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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15857
    Prev
    Next
    INDEX
    Explanations

    dates and temporal markers

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

    Digits "8" or "9" surrounded by other digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.63
    MigrationBuilder
    -1.55
    AddTagHelper
    -1.46
    mybatisplus
    -1.44
     ویکی‌پدیا
    -1.43
    Geplaatst
    -1.43
    #+#
    -1.41
     pinulongan
    -1.40
    GEBURTSDATUM
    -1.37
     itſelf
    -1.37
    POSITIVE LOGITS
     
    1.22
    1
    0.89
    2
    0.78
     "
    0.76
    ↵↵
    0.75
     A
    0.74
    4
    0.72
     (
    0.71
    8
    0.70
    ↵
    0.70
    Activations Density 1.520%

    No Known Activations