© 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. 4937
    Prev
    Next
    INDEX
    Explanations

    indicators of positive experiences or outcomes

    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
    lula
    -0.49
    ⓧ
    -0.45
    WebElementEntity
    -0.45
    łać
    -0.43
     igjen
    -0.43
    chutz
    -0.43
    htu
    -0.43
     belieb
    -0.42
     Siegel
    -0.41
     guardia
    -0.41
    POSITIVE LOGITS
     eventful
    0.82
     punctuated
    0.72
    parsedMessage
    0.71
     fraught
    0.66
    cshtml
    0.65
    insegna
    0.64
    StreetMap
    0.63
     productive
    0.60
    ंदीखरीदारी
    0.58
     fruitful
    0.57
    Activations Density 0.115%

    No Known Activations