© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7001
    Prev
    Next
    INDEX
    Explanations

    details regarding racial identity and heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    cyclic
    -0.39
     Movers
    -0.38
    andi
    -0.37
    isteria
    -0.36
    andia
    -0.36
    MethodManager
    -0.36
    Wilson
    -0.36
    PCS
    -0.35
    大
    -0.34
    Big
    -0.34
    POSITIVE LOGITS
     mixture
    0.86
     mezcla
    0.79
     mixtures
    0.77
     blend
    0.77
     mix
    0.73
     admixture
    0.73
     mixt
    0.73
     mélang
    0.71
     mistura
    0.69
     campuran
    0.68
    Activations Density 0.553%

    No Known Activations