© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    HTML and JSX code structures related to user interfaces

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

    HTML tags, brackets, and styles

    np_acts-logits-general · gemini-2.0-flash

    user, leaves

    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
     intptr
    -0.39
    træ
    -0.29
    tran
    -0.29
    iseite
    -0.27
     勝
    -0.27
    ladung
    -0.26
    pagestyle
    -0.26
    凶
    -0.26
    制
    -0.26
    hauses
    -0.25
    POSITIVE LOGITS
     ModelExpression
    0.74
     createSlice
    0.63
    
    0.60
    Jereo
    0.57
     stanovnika
    0.57
     AssemblyCompany
    0.56
    FormTagHelper
    0.54
     Autorizaciones
    0.53
    AutoModerator
    0.51
    Aiheesta
    0.51
    Activations Density 0.031%

    No Known Activations