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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3748
    Prev
    Next
    INDEX
    Explanations

    connections between elements or concepts in a comparative context

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

    Numbers, especially "two"

    np_acts-logits-general · gemini-2.0-flash

    numbers in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.54
    Aholisi
    -0.50
    medriver
    -0.50
     oprot
    -0.47
    Bjs
    -0.46
     Italijanski
    -0.45
    Firstname
    -0.45
    phosa
    -0.44
    Portail
    -0.44
    ArrowToggle
    -0.44
    POSITIVE LOGITS
     two
    2.41
     three
    1.95
     deux
    1.88
    two
    1.87
     zwei
    1.76
     två
    1.63
     dwóch
    1.61
    两个
    1.57
     trois
    1.55
    兩個
    1.53
    Activations Density 1.272%

    No Known Activations