© 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. 963
    Prev
    Next
    INDEX
    Explanations

    elements that suggest enjoyment or appreciation in a dining or culinary context

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

    Text near periods or commas

    np_acts-logits-general · gemini-2.0-flash

    places and geography

    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
    וך
    -0.59
    śl
    -0.57
    كويكب
    -0.55
    KommentareTeilen
    -0.55
     préférences
    -0.55
     समीक्षक
    -0.54
    tagHelperRunner
    -0.54
     answer
    -0.53
    -};
    -0.52
     VEGAS
    -0.52
    POSITIVE LOGITS
     Located
    1.04
    Located
    1.04
     nearby
    0.98
    Nearby
    0.92
     Nearby
    0.91
     Situated
    0.90
     located
    0.83
    Situated
    0.82
    located
    0.80
    nearby
    0.79
    Activations Density 0.177%

    No Known Activations