© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9951
    Prev
    Next
    INDEX
    Explanations

    elements related to notifications and error messaging in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.71
     autorytatywna
    -0.67
    rrggbb
    -0.62
    principalColumn
    -0.61
    ніципа
    -0.57
    balleur
    -0.57
    évaluateur
    -0.57
     fieldNum
    -0.56
     disambiguazione
    -0.52
     '\\;'
    -0.52
    POSITIVE LOGITS
    makeText
    0.94
    astify
    0.93
    flashdata
    0.60
     flashes
    0.52
    SnackBar
    0.52
    Snackbar
    0.50
     messages
    0.48
    alert
    0.47
     flash
    0.46
    flash
    0.45
    Activations Density 0.143%

    No Known Activations