© 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. 20-GEMMASCOPE-RES-16K
    11. 15108
    Prev
    Next
    INDEX
    Explanations

    phrases indicating states of being or conclusions

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

    Japanese sentence ending particles

    np_acts-logits-general · gemini-2.0-flash

    Japanese sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •korean
    높임말 (honor)

    No Comments

    Negative Logits
    fin
    -0.62
    OGND
    -0.58
    basicConfig
    -0.52
    　　【
    -0.51
     /\.
    -0.50
    }`
    -0.49
    omla
    -0.48
     történ
    -0.48
    BeginInit
    -0.48
    }';
    -0.47
    POSITIVE LOGITS
    FilterChain
    0.63
    EDEFAULT
    0.61
     CreateTagHelper
    0.57
    тельством
    0.56
    fjspx
    0.52
     BrowserModule
    0.51
    Obrázky
    0.50
     initWithFrame
    0.50
    ResponseWriter
    0.50
    matorium
    0.49
    Activations Density 0.046%

    No Known Activations