© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8034
    Prev
    Next
    INDEX
    Explanations

    words related to sorting or categorizing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    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
     EconPapers
    -0.56
     invokingState
    -0.50
    delwed
    -0.42
    httphttps
    -0.41
    Ond
    -0.40
    __':
    -0.39
    JspWriter
    -0.39
    脚注の使い方
    -0.38
    POSITIVE LOGITS
     SORT
    0.84
     sort
    0.83
     Sort
    0.79
    sort
    0.69
     sorting
    0.68
    Sort
    0.68
     sorts
    0.67
     Sorting
    0.66
    SORT
    0.63
     sorta
    0.59
    Activations Density 0.055%

    No Known Activations