© 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. 3527
    Prev
    Next
    INDEX
    Explanations

    ordinal indicators related to numerical rankings or classifications

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

    Numbers with "th" endings

    np_acts-logits-general · gemini-2.0-flash

    ordinal numbers and centuries

    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
     resourceCulture
    -0.79
    RetentionPolicy
    -0.61
    aarrggbb
    -0.58
    usahaan
    -0.58
     ✭✭
    -0.56
    ViewFeatures
    -0.55
    tigung
    -0.54
     ostavi
    -0.54
     consciences
    -0.54
    aluz
    -0.53
    POSITIVE LOGITS
     graders
    0.81
     century
    0.80
    undred
    0.75
     anniversary
    0.73
     grade
    0.72
     percentile
    0.71
    ousand
    0.69
     Century
    0.68
     edition
    0.68
     inning
    0.65
    Activations Density 0.134%

    No Known Activations