© 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. 20-GEMMASCOPE-RES-16K
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    references to animals and animal-related topics

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

    "animal" followed by a specific topic

    np_acts-logits-general · gemini-2.0-flash

    animal studies or research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    ValueStyle
    -0.59
     AssemblyTitle
    -0.58
     eens
    -0.54
     drenched
    -0.53
    OrBuilder
    -0.52
    rrggbb
    -0.52
    edra
    -0.51
    Демографія
    -0.51
    NOWLEDGE
    -0.50
     lift
    -0.49
    POSITIVE LOGITS
     Animals
    0.80
    cules
    0.74
     ANIMALS
    0.73
    Animals
    0.71
    Animal
    0.70
    animals
    0.70
     animals
    0.70
     BoxFit
    0.69
     cruelty
    0.68
     Animal
    0.67
    Activations Density 0.126%

    No Known Activations