© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 74156
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structures

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

    start of turn user

    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
    AddTagHelper
    -0.99
     Normdatei
    -0.96
     صوتيه
    -0.94
     Theſe
    -0.89
     indígen
    -0.89
    transQ
    -0.89
     ujednoznacz
    -0.88
     يتيمه
    -0.86
    ArgsConstructor
    -0.85
     Anſ
    -0.84
    POSITIVE LOGITS
     
    0.67
    .
    0.65
     a
    0.61
    '
    0.52
     the
    0.52
     \
    0.51
     official
    0.50
     electronic
    0.50
      
    0.49
     "
    0.49
    Activations Density 0.018%

    No Known Activations