© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 332
    Prev
    Next
    INDEX
    Explanations

    phrases related to damage and repair

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

    themes of irreparable damage or loss

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

    repair or fix

    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
     defaultstate
    -0.54
    buz
    -0.51
     laude
    -0.49
     Stok
    -0.49
    发表于
    -0.46
    roud
    -0.45
     gola
    -0.44
    metheus
    -0.44
     withdrawing
    -0.44
    SNE
    -0.44
    POSITIVE LOGITS
     repair
    2.33
     repairs
    2.14
     Repair
    2.13
     repaired
    2.08
    repair
    2.05
    Repair
    2.03
     REPAIR
    1.98
     repairing
    1.96
     Repairs
    1.89
     réparation
    1.67
    Activations Density 0.143%

    No Known Activations