© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1962
    Prev
    Next
    INDEX
    Explanations

    references to institutional racism and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Terms related to racial integration and civil rights

    np_acts-logits-general · gemini-2.0-flash

    civil rights and segregation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.69
    >{@
    -0.68
    îtra
    -0.56
    zungs
    -0.55
    wpi
    -0.52
    zcan
    -0.52
     narcissistic
    -0.51
     cornu
    -0.50
     gaga
    -0.49
    didSet
    -0.48
    POSITIVE LOGITS
     integration
    1.20
     integrated
    1.08
     integrate
    1.08
     Integration
    1.06
     civil
    1.04
     segregation
    1.04
    Integration
    0.97
     racial
    0.97
     integrating
    0.96
     Civil
    0.96
    Activations Density 0.503%

    No Known Activations