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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7065
    Prev
    Next
    INDEX
    Explanations

    patterns in numerical sequences

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

    Hexadecimal and numerical sequences starting with "0x01"

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and punctuation

    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
     يتيمه
    -0.61
     estekak
    -0.60
    Hentet
    -0.59
     uſe
    -0.59
     الحره
    -0.58
     chofe
    -0.57
    YourGuide
    -0.54
    homonymie
    -0.54
    Sizer
    -0.54
     isInitialized
    -0.53
    POSITIVE LOGITS
     protoimpl
    0.61
    ViewFeatures
    0.59
    makeText
    0.53
     defaultstate
    0.50
     ویکی‌پدی
    0.49
    mergeFrom
    0.48
    IndentedString
    0.48
     final
    0.48
    opardy
    0.48
    numerusform
    0.46
    Activations Density 0.154%

    No Known Activations