© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2075
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numbers and their significance in various contexts

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

    "first" followed by other words

    np_acts-logits-general · gemini-2.0-flash

    first part or section

    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
    adaptiveStyles
    -0.59
     ujednoznacz
    -0.58
     Wiktionnaire
    -0.55
     []:
    -0.53
     okuyayım
    -0.52
    ChildScrollView
    -0.49
    vismo
    -0.49
     HttpNotFound
    -0.48
     saites
    -0.48
    withCredentials
    -0.47
    POSITIVE LOGITS
     part
    0.92
     two
    0.87
     few
    0.84
     half
    0.83
     portion
    0.78
    Архівовано
    0.74
     three
    0.73
     four
    0.72
     section
    0.70
     leg
    0.69
    Activations Density 0.474%

    No Known Activations