© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11176
    Prev
    Next
    INDEX
    Explanations

    phrases that include "who" and variations of it, indicating a focus on people and their roles or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retz
    -0.44
     Sanford
    -0.44
    发表于
    -0.43
    enta
    -0.38
    fall
    -0.38
    lt
    -0.38
    ctest
    -0.37
    feldt
    -0.37
    lis
    -0.37
     Dunlap
    -0.37
    POSITIVE LOGITS
     who
    1.42
     Who
    1.15
    Who
    1.13
     którzy
    1.11
    who
    1.09
     whom
    1.03
     kteří
    1.01
     quien
    0.98
     quienes
    0.93
     quién
    0.92
    Activations Density 0.156%

    No Known Activations