© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 4624
    Prev
    Next
    INDEX
    Explanations

    concepts related to equality and fairness in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favorable
    -0.86
    favorable
    -0.83
     favorably
    -0.82
     favorite
    -0.77
     uș
    -0.77
    Favorite
    -0.76
     enggak
    -0.75
     și
    -0.75
    favorite
    -0.74
     rumors
    -0.74
    POSITIVE LOGITS
    Whilst
    1.22
     Whilst
    1.19
     whilst
    1.03
     characterised
    0.99
     recognisable
    0.93
    initialise
    0.90
     realisation
    0.87
     recognise
    0.87
     recognising
    0.87
     generalised
    0.87
    Activations Density 0.664%

    No Known Activations