© 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. 14600
    Prev
    Next
    INDEX
    Explanations

    technical issues related to programming and software development errors

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

    Requests for help or suggestions

    np_acts-logits-general · gemini-2.0-flash

    seeking help and solutions

    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
     שוליים
    -0.42
     alimentaria
    -0.40
     '?'
    -0.36
     "$@"
    -0.36
     blockSize
    -0.33
    astify
    -0.33
    mCamera
    -0.32
     anzeigen
    -0.31
    ︎
    -0.31
     naturalmente
    -0.30
    POSITIVE LOGITS
     troubleshoot
    0.58
     workaround
    0.57
     troubleshooting
    0.57
    Troubleshooting
    0.52
    lujah
    0.50
     Troubleshooting
    0.48
    tutorials
    0.48
     Weizen
    0.47
     debugging
    0.47
     Frust
    0.47
    Activations Density 0.717%

    No Known Activations