© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13433
    Prev
    Next
    INDEX
    Explanations

    references to topics surrounding race and social inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consape
    -0.48
    かなり
    -0.48
    はかなり
    -0.46
    かなりの
    -0.43
    相當
    -0.43
     dürfte
    -0.42
     IMHO
    -0.42
     oldukça
    -0.41
     IMO
    -0.41
    可以说
    -0.39
    POSITIVE LOGITS
     supposedly
    1.35
     яко
    1.20
     supuestamente
    1.17
     somehow
    1.14
     angeb
    1.14
     allegedly
    1.10
     supposed
    0.97
    supposed
    0.94
     purported
    0.94
     údaj
    0.90
    Activations Density 1.254%

    No Known Activations