© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    code formatting elements or code blocks

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

    Code snippets and file paths

    np_acts-logits-general · gemini-2.0-flash

    programming and code references

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DNEY
    -0.63
    ONY
    -0.58
    Достоинства
    -0.57
     Blanchard
    -0.57
     LeBlanc
    -0.56
    tempted
    -0.55
    حياته
    -0.54
     treo
    -0.52
    Склад
    -0.51
    UnknownFieldSet
    -0.50
    POSITIVE LOGITS
    Personensuche
    0.56
     مرئيه
    0.55
     оригіналу
    0.54
    ViewImports
    0.52
    \]
    0.52
    ViewSet
    0.51
    zzleHttp
    0.50
    httphttps
    0.50
     препратки
    0.50
    참고
    0.48
    Activations Density 0.029%

    No Known Activations