© 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. 6828
    Prev
    Next
    INDEX
    Explanations

    references to athletes and their performance in sports

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

    Future tense expressed with "will"

    np_acts-logits-general · gemini-2.0-flash

    will be

    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
    SourceChecksum
    -0.81
     تضيفلها
    -0.77
     Eventually
    -0.68
     ProtoMessage
    -0.67
    RetentionPolicy
    -0.66
     виправивши
    -0.66
    eventually
    -0.66
     periods
    -0.64
     eventually
    -0.63
     mergeFrom
    -0.63
    POSITIVE LOGITS
     hoping
    0.87
    Hoping
    0.77
     Hoping
    0.76
    Expect
    0.74
     hopes
    0.73
     aiming
    0.68
     Expect
    0.67
    expect
    0.67
     expectation
    0.66
     expecting
    0.65
    Activations Density 0.159%

    No Known Activations