© 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. 22-GEMMASCOPE-RES-16K
    11. 5566
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their combinations in the text

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

    "and" followed by a food-related term

    np_acts-logits-general · gemini-2.0-flash

    food and beverages

    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
    displayquote
    -0.51
    }}}}
    -0.51
    itets
    -0.49
    RowIndex
    -0.49
    дельник
    -0.46
    adpleegd
    -0.45
     --
    -0.45
     padx
    -0.45
    Искәрмәләр
    -0.44
    guém
    -0.44
    POSITIVE LOGITS
    IntoConstraints
    0.86
     GenerationType
    0.73
    DoubleQuotes
    0.73
     ſche
    0.66
    TagHelpers
    0.66
    setVerticalGroup
    0.65
    UNRELATED
    0.65
    endphp
    0.64
    XmlAccessorType
    0.64
     DBNull
    0.64
    Activations Density 0.334%

    No Known Activations