© 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. 8699
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political action

    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
    Diweddarwch
    -0.75
    AutoScaleMode
    -0.70
     سكانية
    -0.68
    ValueStyle
    -0.59
    writeFieldEnd
    -0.58
    EndGlobalSection
    -0.58
    хьтан
    -0.57
    SourceChecksum
    -0.56
     незавершена
    -0.56
     Wicidata
    -0.51
    POSITIVE LOGITS
     hundreds
    2.38
     dozens
    2.09
    hundreds
    2.00
     thousands
    1.96
     Hundreds
    1.87
    Hundreds
    1.87
     ratusan
    1.68
    thousands
    1.66
     centaines
    1.61
    数百
    1.59
    Activations Density 1.510%

    No Known Activations