© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3185
    Prev
    Next
    INDEX
    Explanations

    information related to hiring practices and employment discrimination

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

    phrases and contexts related to hiring, employment decisions, and job recruitment.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedSize
    -0.38
    RTLR
    -0.38
    gameserver
    -0.38
    govina
    -0.36
    MessageWindow
    -0.35
    SourceChecksum
    -0.35
    ukone
    -0.35
     ModelExpression
    -0.35
    nání
    -0.34
    Marshaller
    -0.34
    POSITIVE LOGITS
     hiring
    2.63
     Hiring
    2.25
     hire
    2.23
    Hiring
    2.22
     hires
    2.20
     recruitment
    2.16
     recruiting
    2.13
     recruit
    2.08
     hired
    2.02
     recruited
    1.91
    Activations Density 0.521%

    No Known Activations