© 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. 487
    Prev
    Next
    INDEX
    Explanations

    instances of the word "made" and its variations indicating creation or formation

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

    actions indicating creation or production

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

    make a or make sure

    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
    cheme
    -0.59
    árbol
    -0.57
    lámpara
    -0.57
     réussite
    -0.56
     hilt
    -0.56
    Vidite
    -0.55
     SWR
    -0.54
     étrangère
    -0.54
     boî
    -0.54
    botella
    -0.54
    POSITIVE LOGITS
    simpleType
    0.56
    tanleria
    0.54
     autorytatywna
    0.53
    BlockPos
    0.50
    Спасылкі
    0.49
    openzeppelin
    0.49
     camp
    0.45
    MetaObject
    0.45
    +#+#
    0.45
     plans
    0.44
    Activations Density 0.030%

    No Known Activations