© 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. 35-GEMMASCOPE-RES-16K
    11. 10515
    Prev
    Next
    INDEX
    Explanations

    language related to poverty and economic disparity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     سات
    -0.31
     Schützen
    -0.29
    başı
    -0.28
    urut
    -0.27
    lauf
    -0.27
    ądz
    -0.27
     tampering
    -0.27
     пробу
    -0.26
    ĩnh
    -0.26
     pép
    -0.26
    POSITIVE LOGITS
     poor
    2.58
    poor
    2.38
     poverty
    2.38
    Poor
    2.38
     Poor
    2.30
     POOR
    2.16
     poorest
    2.11
    poverty
    2.08
     pobres
    2.08
     impoverished
    2.06
    Activations Density 0.727%

    No Known Activations