© 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. 33-GEMMASCOPE-RES-16K
    11. 9699
    Prev
    Next
    INDEX
    Explanations

    phrases related to the importance of community and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.66
     MainAxisSize
    -0.62
    selaer
    -0.60
     Italijanski
    -0.59
    pushFollow
    -0.59
     IFTT
    -0.57
    RegressionTest
    -0.57
    Дереккөздер
    -0.56
     propOrder
    -0.56
    transQ
    -0.55
    POSITIVE LOGITS
     Gegend
    0.34
    เอา
    0.33
    ParallelGroup
    0.33
     deberes
    0.32
     aprobación
    0.32
     jedin
    0.32
     debió
    0.31
     contratación
    0.31
    tagHelperRunner
    0.31
    berday
    0.31
    Activations Density 0.090%

    No Known Activations