© 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. 21-GEMMASCOPE-RES-16K
    11. 13364
    Prev
    Next
    INDEX
    Explanations

    references to various product names and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     industriel
    -0.38
     advertencia
    -0.37
     extracción
    -0.36
     humaines
    -0.36
     indépendant
    -0.36
     publicitaires
    -0.32
     oscuridad
    -0.32
     culturel
    -0.32
     inspección
    -0.31
     lección
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.82
    featureID
    0.81
     autorytatywna
    0.79
    StoryboardSegue
    0.75
     esternos
    0.74
    InitVars
    0.72
    AndEndTag
    0.71
     Paglinawan
    0.71
    Jeografia
    0.71
    AccessorTable
    0.70
    Activations Density 0.353%

    No Known Activations