© 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. 14-GEMMASCOPE-RES-16K
    11. 3423
    Prev
    Next
    INDEX
    Explanations

    emotions or descriptors related to feelings and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.93
    +#+#
    -0.90
    expandindo
    -0.87
    Hochspringen
    -0.79
    testens
    -0.79
    transQ
    -0.74
    ArgsConstructor
    -0.73
    MLLoader
    -0.73
     betweenstory
    -0.72
     Paglinawan
    -0.69
    POSITIVE LOGITS
     even
    0.68
     almost
    0.62
     it
    0.56
     could
    0.55
     cant
    0.53
     nearly
    0.52
     no
    0.51
     couldn
    0.50
     mungkin
    0.50
     даже
    0.50
    Activations Density 0.165%

    No Known Activations