© 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. 8150
    Prev
    Next
    INDEX
    Explanations

    numerical values or references

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

    Code snippets containing "private"

    np_acts-logits-general · gemini-2.0-flash

    legal and programming contexts

    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
    Xuất
    -0.59
    MemoryWarning
    -0.59
    NewGuid
    -0.57
    AddWithValue
    -0.56
     Parac
    -0.56
    ExecuteReader
    -0.55
     EnglishChoose
    -0.55
    TintMode
    -0.54
     Muta
    -0.53
     Goul
    -0.52
    POSITIVE LOGITS
     <=",
    0.69
    はじめに
    0.61
    awtextra
    0.56
    сылкі
    0.55
     通販
    0.50
    IGATION
    0.46
    haber
    0.46
    uxx
    0.46
                              
    0.45
    inary
    0.45
    Activations Density 0.285%

    No Known Activations