© 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. 0-GEMMASCOPE-RES-65K
    11. 9362
    Prev
    Next
    INDEX
    Explanations

    instances or mentions of "large" or sizable quantities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.85
    parsedMessage
    -0.84
    saraba
    -0.75
     doccia
    -0.73
     supérieurs
    -0.73
     supérieures
    -0.72
    GEBURTSDATUM
    -0.71
    RegistryLite
    -0.71
     réalisateur
    -0.70
    MemoryWarning
    -0.69
    POSITIVE LOGITS
     large
    2.16
     Large
    1.98
    large
    1.91
    Large
    1.82
     LARGE
    1.65
     small
    1.41
    LARGE
    1.24
     Small
    1.21
    Small
    1.16
    small
    1.12
    Activations Density 0.095%

    No Known Activations