© 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. 41-GEMMASCOPE-RES-16K
    11. 10497
    Prev
    Next
    INDEX
    Explanations

    references to political oppression and social issues related to governance and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.57
    hip
    -0.47
    性
    -0.41
    ity
    -0.41
    ervant
    -0.40
     defaultstate
    -0.39
     typelib
    -0.39
    化
    -0.39
    localctx
    -0.38
    적인
    -0.38
    POSITIVE LOGITS
    ities
    1.20
    ments
    1.16
    ths
    1.07
    nesses
    1.07
    ings
    1.05
    hips
    1.02
    ures
    1.02
    ches
    1.02
    aries
    1.01
    ages
    1.00
    Activations Density 1.617%

    No Known Activations