© 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. 295
    Prev
    Next
    INDEX
    Explanations

    conjunctions and terms related to nutritional measurements

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

    conjunctions and their variations

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

    independent and specific terms

    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
    intent
    -0.70
     Funnel
    -0.69
     antenna
    -0.66
     Ansel
    -0.66
     antennas
    -0.64
     anthony
    -0.64
     Lent
    -0.63
     funnel
    -0.63
     Wendell
    -0.62
     sanding
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.63
    EDEFAULT
    0.58
    最快更新
    0.49
    maro
    0.47
     плат
    0.45
    resave
    0.45
    wier
    0.45
    äuser
    0.45
     Wicidata
    0.45
    AccessorTable
    0.45
    Activations Density 0.192%

    No Known Activations