© 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. 24-GEMMASCOPE-RES-16K
    11. 1390
    Prev
    Next
    INDEX
    Explanations

    recommendations and decisions related to product choices and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding a verb in the infinitive form

    np_acts-logits-general · gemini-2.0-flash

    modal verb followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.60
    RectangleBorder
    -0.58
    BeginInit
    -0.54
    terima
    -0.53
    expandindo
    -0.53
    Хьажоргаш
    -0.52
    lamó
    -0.52
     convenable
    -0.51
    )|^{
    -0.51
    suporte
    -0.50
    POSITIVE LOGITS
     opt
    1.03
     opting
    0.99
     stick
    0.94
     opted
    0.91
     sticking
    0.90
     skip
    0.88
     optar
    0.81
     opts
    0.79
     skipping
    0.79
     EconPapers
    0.78
    Activations Density 0.281%

    No Known Activations