© 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. 10-GEMMASCOPE-RES-16K
    11. 8346
    Prev
    Next
    INDEX
    Explanations

    phrases that describe individuals and their traits or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sanford
    -0.49
    tart
    -0.47
    ert
    -0.47
     Leland
    -0.47
    lt
    -0.46
    ting
    -0.46
     Lath
    -0.46
    发表于
    -0.45
    tle
    -0.44
    ignet
    -0.44
    POSITIVE LOGITS
     who
    1.32
     Who
    1.05
    Who
    1.04
     którzy
    1.03
    who
    1.00
     quien
    0.98
     kteří
    0.95
     whom
    0.94
    quien
    0.88
     WHO
    0.84
    Activations Density 0.180%

    No Known Activations