© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10458
    Prev
    Next
    INDEX
    Explanations

    components related to programming syntax and structure

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

    Code snippets or special characters

    np_acts-logits-general · gemini-2.0-flash

    order in unique identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     surla
    -0.75
    脚注の使い方
    -0.75
    
    -0.74
    MigrationBuilder
    -0.69
     otomatig
    -0.68
    Hauptartikel
    -0.66
    Autoritní
    -0.64
     विश्वसनीयता
    -0.64
    aarrggbb
    -0.62
    MessageOf
    -0.62
    POSITIVE LOGITS
    wich
    0.31
     dunque
    0.30
     localObject
    0.29
    lanması
    0.29
     mut
    0.28
     مول
    0.27
     lasci
    0.26
     therefore
    0.26
    对其
    0.26
     therefor
    0.26
    Activations Density 0.161%

    No Known Activations