© 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. 7790
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions or reactions in dialogue

    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
     BoxFit
    -0.70
    ----</
    -0.68
    GraphicsUnit
    -0.65
    Diweddarwch
    -0.65
    oredCriteria
    -0.64
     linkovi
    -0.63
    IGENCE
    -0.63
     AssemblyCulture
    -0.63
    
    -0.62
    sizeCache
    -0.61
    POSITIVE LOGITS
     oh
    2.19
     Oh
    2.00
    Oh
    1.86
    oh
    1.69
     wow
    1.66
     ah
    1.60
     Ah
    1.53
     Wow
    1.52
     Ooh
    1.52
    Ah
    1.49
    Activations Density 0.634%

    No Known Activations