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

    Neuronpedia

    Jacobian LensNEW
    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. 13264
    Prev
    Next
    INDEX
    Explanations

    references to dog behaviors and interactions

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

    dogs

    np_acts-logits-general · gemini-2.0-flash

    dog or dogs

    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
     дописавши
    -0.98
    +#+#
    -0.82
     EconPapers
    -0.72
    BufferException
    -0.71
     ویکی‌پدیای
    -0.67
    éron
    -0.65
    GOTREF
    -0.63
    Tembelea
    -0.59
    contentLoaded
    -0.59
    énario
    -0.58
    POSITIVE LOGITS
     dog
    1.95
     dogs
    1.87
     Dog
    1.69
     Dogs
    1.69
     canine
    1.66
    Dog
    1.63
    Dogs
    1.62
     DOG
    1.57
    dog
    1.56
     Canine
    1.51
    Activations Density 0.307%

    No Known Activations