© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11468
    Prev
    Next
    INDEX
    Explanations

    numeric and formatting structures in text

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

    Uncommon characters or symbols

    np_acts-logits-general · gemini-2.0-flash

    programming, covid, and unicode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.68
    httphttps
    -0.63
    richTextPanel
    -0.57
    delwed
    -0.54
    InputTagHelper
    -0.52
    CROSSTALK
    -0.51
    "}\
    -0.50
     defaultstate
    -0.48
    MessageOf
    -0.47
    ("}\
    -0.47
    POSITIVE LOGITS
      
    0.54
    क़
    0.48
    autogui
    0.47
       
    0.45
     bbq
    0.45
    stdint
    0.44
     Covid
    0.44
     COVID
    0.43
     ​
    0.43
    openzeppelin
    0.42
    Activations Density 0.843%

    No Known Activations