© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15013
    Prev
    Next
    INDEX
    Explanations

    topics related to legal decisions surrounding affirmative action and race in admissions policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.74
    iasis
    -0.57
    [++
    -0.55
     typelib
    -0.55
    DotNetBar
    -0.53
    Cyfeiriadau
    -0.51
    Cubit
    -0.50
    WebVitals
    -0.48
     cucharadas
    -0.47
    Schemes
    -0.47
    POSITIVE LOGITS
     ruling
    1.10
    ruling
    0.97
     argued
    0.95
     arguments
    0.93
     upholding
    0.90
     upheld
    0.90
     rulings
    0.89
     argument
    0.88
     challenge
    0.88
     Arguments
    0.86
    Activations Density 2.123%

    No Known Activations