© 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. 13-GEMMASCOPE-RES-65K
    6. 38107
    Prev
    Next
    INDEX
    Explanations

    references to a malfunctioning machine or device

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rapnel
    -0.47
     grecque
    -0.44
     debate
    -0.44
    出版年
    -0.43
    ourced
    -0.43
    bability
    -0.43
    Décès
    -0.42
    isle
    -0.41
    lamic
    -0.41
    stol
    -0.41
    POSITIVE LOGITS
     parseFrom
    0.77
    SBATCH
    0.73
     pinulongan
    0.68
     useAppContext
    0.67
     endwhile
    0.65
    FieldNumber
    0.62
    хьтан
    0.61
    adpleegd
    0.61
    ItemBackground
    0.60
     comigo
    0.59
    Activations Density 0.032%

    No Known Activations