© 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. 22-GEMMASCOPE-RES-16K
    11. 6665
    Prev
    Next
    INDEX
    Explanations

    elements related to documentation and instructions

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

    German and Japanese passive voice verbs

    np_acts-logits-general · gemini-2.0-flash

    created, deleted, sent, discovered, killed, passed away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.63
    SharedCtor
    -0.60
     المعيارى
    -0.57
    AddTagHelper
    -0.56
     незавершена
    -0.54
     AssemblyCulture
    -0.53
     autorytatywna
    -0.51
     VizieR
    -0.50
     ligiloj
    -0.49
    ोंने
    -0.49
    POSITIVE LOGITS
     worden
    0.97
     wordt
    0.94
     werden
    0.86
     wird
    0.83
     được
    0.78
     werd
    0.73
    wird
    0.69
    werd
    0.65
    werden
    0.65
     becomes
    0.64
    Activations Density 0.068%

    No Known Activations