© 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. 20-GEMMASCOPE-RES-16K
    11. 14838
    Prev
    Next
    INDEX
    Explanations

    references to dogs

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

    "dog" (and its capitalization variants)

    np_acts-logits-general · gemini-2.0-flash

    dog fighting

    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
    •dogs

    No Comments

    Negative Logits
     EconPapers
    -0.81
    \{\\
    -0.81
     snippetHide
    -0.74
    AutoresizingMask
    -0.71
    Життєпис
    -0.71
    ValueStyle
    -0.70
    Demografia
    -0.66
     للمعارف
    -0.63
    Surge
    -0.63
    enumi
    -0.60
    POSITIVE LOGITS
     ​​
    0.70
    fight
    0.62
     dogs
    0.59
     Dog
    0.59
     Dogs
    0.57
    Dog
    0.57
    Dogs
    0.56
    dogs
    0.53
    ijuana
    0.52
    ">//
    0.51
    Activations Density 0.053%

    No Known Activations