© 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. 3593
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watch" and its variations in context

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

    "watch" (or "Watch") in various contexts

    np_acts-logits-general · gemini-2.0-flash

    watching words and phrases

    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
    teries
    -0.68
    AddTagHelper
    -0.66
     Abp
    -0.65
    ◆◆
    -0.65
    ArgsConstructor
    -0.61
    cline
    -0.55
    ."],
    -0.53
    />";
    -0.53
     оригіналу
    -0.52
     EClass
    -0.52
    POSITIVE LOGITS
    tower
    0.90
     atenta
    0.79
    towers
    0.78
    dogs
    0.76
     helplessly
    0.67
    dog
    0.66
    DOG
    0.61
    👀
    0.60
    Dog
    0.59
     closely
    0.59
    Activations Density 0.148%

    No Known Activations