© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    specific technical terminology and classifications related to materials and structural components

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

    Non-English word beginnings

    np_acts-logits-general · gemini-2.0-flash

    striking with borders or edges

    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
    onActivityResult
    -0.46
    addGroup
    -0.46
     scio
    -0.46
    InstanceState
    -0.45
     arbitrage
    -0.44
    axios
    -0.44
    cein
    -0.44
     vedo
    -0.43
    CompilerServices
    -0.43
    readystatechange
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.70
     שוליים
    0.65
    unnitel
    0.64
    #+#
    0.64
    MessageTagHelper
    0.62
     Suède
    0.61
    :+:
    0.58
    例文帳に追加
    0.57
     disambiguazione
    0.56
    
    0.56
    Activations Density 0.257%

    No Known Activations