© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81513
    Prev
    Next
    INDEX
    Explanations

    various forms of formatting and structural elements in code or markup

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

    Docker networks

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    EndProject
    -0.76
     Normdatei
    -0.73
     Autorizaciones
    -0.66
    httphttps
    -0.64
    +:+
    -0.64
    StoreMessageInfo
    -0.63
    Ⴈ
    -0.63
     endfor
    -0.62
    TypedDataSet
    -0.60
    eaways
    -0.60
    POSITIVE LOGITS
     u
    0.33
    那就
    0.31
     i
    0.29
     очистки
    0.28
      
    0.28
    úng
    0.28
    Much
    0.27
     miscellaneous
    0.27
     much
    0.27
     viewDidLoad
    0.27
    Activations Density 0.035%

    No Known Activations