© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9566
    Prev
    Next
    INDEX
    Explanations

    the word "Top" and its associations in various contexts

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

    "Top" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    top + various specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hysema
    -0.46
    AnchorStyles
    -0.46
     Robles
    -0.45
    params
    -0.45
    stanz
    -0.45
    kenalkan
    -0.45
    صادر
    -0.44
    osť
    -0.44
    emang
    -0.44
    ograma
    -0.44
    POSITIVE LOGITS
    notch
    1.03
     notch
    1.00
     TOP
    0.89
     tier
    0.85
    most
    0.84
     priority
    0.79
     brass
    0.79
     tops
    0.78
     Notch
    0.78
    secret
    0.77
    Activations Density 0.091%

    No Known Activations