© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 49
    Prev
    Next
    INDEX
    Explanations

    references to factions and expansions in role-playing games

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

    elements related to combat and factions in a fantasy setting

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

    proper nouns and place names

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    >{@
    -0.80
     חיצוניים
    -0.70
    Aiheesta
    -0.66
     المعيارى
    -0.66
    glTexCoord
    -0.63
    spesies
    -0.60
     Fitch
    -0.58
     שוליים
    -0.56
    hyrchwyd
    -0.56
    onade
    -0.56
    POSITIVE LOGITS
     Carlisle
    0.62
     Cumbria
    0.60
     Okan
    0.53
     Aene
    0.52
     xr
    0.51
     Skyrim
    0.50
     Beatrix
    0.49
     Oculus
    0.48
     Cumberland
    0.47
     beatles
    0.47
    Activations Density 0.070%

    No Known Activations