© 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. 33-GEMMASCOPE-RES-16K
    11. 7407
    Prev
    Next
    INDEX
    Explanations

    affirmative language indicating presence or qualities of individuals and organizations

    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
     يتيمه
    -0.57
     ujednoznacz
    -0.50
     disambiguazione
    -0.50
    دانشنامهٔ
    -0.48
    ніципалі
    -0.46
    NameInMap
    -0.44
     дописавши
    -0.44
    sizeCache
    -0.42
    RegressionTest
    -0.42
     Containing
    -0.42
    POSITIVE LOGITS
     committed
    0.91
     passionate
    0.67
     proud
    0.67
     striving
    0.67
    committed
    0.66
     fortunate
    0.65
     aware
    0.65
     constantly
    0.63
     accustomed
    0.61
     Committed
    0.59
    Activations Density 0.372%

    No Known Activations