© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7939
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and efficiency

    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
     propOrder
    -0.43
     أعلام
    -0.34
     مواليد
    -0.34
    цездатний
    -0.34
    assertNotNull
    -0.33
    cemment
    -0.31
    enough
    -0.31
    المناصب
    -0.30
     intends
    -0.30
     ernst
    -0.30
    POSITIVE LOGITS
     cumbersome
    1.31
     hassle
    1.28
     tedious
    1.27
     laborious
    1.21
     costly
    1.14
     inconvenience
    1.11
     inconvenient
    1.11
     expensive
    1.06
     Aufwand
    1.01
     headache
    1.00
    Activations Density 1.173%

    No Known Activations