© 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. 25-GEMMASCOPE-RES-16K
    11. 15773
    Prev
    Next
    INDEX
    Explanations

    references to social status and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    高端
    -0.44
    thansa
    -0.43
     mewah
    -0.43
    zydent
    -0.43
    adpleegd
    -0.43
    ACHUSETTS
    -0.41
     Adults
    -0.40
     stately
    -0.40
    奏
    -0.40
     advanced
    -0.40
    POSITIVE LOGITS
     humble
    0.86
     lowly
    0.86
     cheap
    0.85
     humb
    0.85
     poorer
    0.79
    cheap
    0.76
     cheaper
    0.73
    Cheap
    0.72
     inexpensive
    0.71
     plebe
    0.70
    Activations Density 0.642%

    No Known Activations