© 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. 3829
    Prev
    Next
    INDEX
    Explanations

    instances of the word "feed" in various contexts, indicating a focus on feeding systems or networks

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

    Text containing "feed" or "fed"

    np_acts-logits-general · gemini-2.0-flash

    feed forward network

    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
     تضيفلها
    -0.52
    География
    -0.52
    shadowColor
    -0.50
    +#+
    -0.49
    nalités
    -0.49
    ٰ
    -0.48
    Phaser
    -0.47
    scriptcase
    -0.47
     tercio
    -0.47
    циона
    -0.47
    POSITIVE LOGITS
     Feed
    1.28
     feed
    1.23
     feeds
    1.22
     Feeds
    1.19
     FEED
    1.16
    Feed
    1.12
    feeds
    1.08
    FEED
    1.06
    feed
    1.06
    Feeds
    1.05
    Activations Density 0.082%

    No Known Activations