© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    terms related to dogs and their training or behavioral characteristics

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

    after "your" or related to "dogs"

    np_acts-logits-general · gemini-2.0-flash

    dogs and pets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.68
    adaptiveStyles
    -0.64
    ]")]
    -0.62
     initComponents
    -0.60
    Демографія
    -0.60
     дописавши
    -0.59
    ỡng
    -0.59
    laken
    -0.57
     AssemblyCulture
    -0.57
    awtextra
    -0.57
    POSITIVE LOGITS
     dogs
    2.25
     dog
    2.09
     pets
    2.03
     Dogs
    1.83
     animals
    1.81
     pet
    1.80
    Dogs
    1.76
     canine
    1.73
     animal
    1.71
     Dog
    1.70
    Activations Density 0.538%

    No Known Activations