© 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. 20-GEMMASCOPE-RES-16K
    6. 7980
    Prev
    Next
    INDEX
    Explanations

    phrases indicating types or categories of things

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

    "of" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    type of followed by category

    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
     colère
    -0.60
     suficientes
    -0.59
     volontà
    -0.59
    OGND
    -0.57
     necessárias
    -0.56
     générations
    -0.56
     isolada
    -0.56
     singoli
    -0.54
     concetto
    -0.53
     atât
    -0.53
    POSITIVE LOGITS
     FetchType
    0.83
    uesday
    0.79
     createState
    0.78
    ')";
    0.75
    }}]{
    0.73
    MessageOf
    0.70
    )':
    0.69
    ^(@)
    0.69
    ">',
    0.69
    "):
    
    0.68
    Activations Density 0.216%

    No Known Activations