© 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 EvalsExportsinterp-engineNEWAPI 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. 5691
    Prev
    Next
    INDEX
    Explanations

    references to media reports and publications

    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
    getCmp
    -0.38
     Koffer
    -0.36
     bambú
    -0.36
     amistad
    -0.36
     actores
    -0.35
    bindingNavigator
    -0.35
     Família
    -0.34
     polaire
    -0.34
     للمعارف
    -0.34
     volunteer
    -0.34
    POSITIVE LOGITS
     Reuters
    1.26
     CNN
    1.20
     Newsweek
    1.16
     Bloomberg
    1.12
    Reuters
    1.08
     Times
    1.07
     CNBC
    1.07
     Huffington
    1.06
     BBC
    1.06
     Daily
    1.06
    Activations Density 0.845%

    No Known Activations