© 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. 13-GEMMASCOPE-RES-65K
    11. 5152
    Prev
    Next
    INDEX
    Explanations

    names of characters and significant entities from various narratives or contexts

    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
    ']],
    -0.61
    >]
    -0.56
    }}}\
    -0.55
     betweenstory
    -0.54
    hadur
    -0.53
    ERÍA
    -0.52
     quantity
    -0.51
    gridy
    -0.51
    textra
    -0.51
     BRARY
    -0.50
    POSITIVE LOGITS
     himself
    0.72
     thyself
    0.66
     Himself
    0.65
     defaultstate
    0.62
    PreExecute
    0.62
    ఔ
    0.59
    himself
    0.59
    ’
    0.58
    MemoryWarning
    0.57
    حياته
    0.55
    Activations Density 0.054%

    No Known Activations