© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    references to social issues, particularly slavery and racism, as well as systemic inequality and media representation

    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
    
    -0.45
    BeginContext
    -0.41
    avo
    -0.34
    linspace
    -0.33
    ane
    -0.33
    EndInit
    -0.32
    Dienstag
    -0.32
    médiaire
    -0.32
    arange
    -0.31
    Inhoud
    -0.31
    POSITIVE LOGITS
     round
    1.09
     nonstop
    1.02
     anytime
    0.96
    ตลอด
    0.95
    round
    0.92
     constant
    0.91
     CONSTANT
    0.88
     Anytime
    0.86
     constantly
    0.84
     dø
    0.84
    Activations Density 0.288%

    No Known Activations