© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11695
    Prev
    Next
    INDEX
    Explanations

    references to emotional and engaging performances or artistic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.60
    DebuggerNonUser
    -0.57
    Raycast
    -0.51
     rowspan
    -0.50
     ouver
    -0.47
    TagHelper
    -0.47
    ashian
    -0.47
    ソナ
    -0.46
     mögen
    -0.45
    kie
    -0.45
    POSITIVE LOGITS
     wow
    1.05
     enchant
    0.97
     delight
    0.97
     mesmer
    0.97
     captiv
    0.92
     tantal
    0.90
     impress
    0.90
     WOW
    0.86
     captivated
    0.83
    wow
    0.83
    Activations Density 0.206%

    No Known Activations