© 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. 10-GEMMASCOPE-RES-16K
    11. 8187
    Prev
    Next
    INDEX
    Explanations

    the start of new sections or paragraphs in a document, indicated by the "<bos>" token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.52
    TagMode
    -0.50
    $__
    -0.44
     manualmente
    -0.43
     protoimpl
    -0.40
     steder
    -0.40
     igjen
    -0.37
     implementación
    -0.37
     polizia
    -0.37
     sensibilité
    -0.36
    POSITIVE LOGITS
    Hochspringen
    0.65
    featureID
    0.63
    PerformLayout
    0.62
     للمعارف
    0.56
    Portail
    0.52
    TagHelper
    0.51
    ChildScrollView
    0.51
    fjspx
    0.51
     ujednoznacz
    0.50
     autorytatywna
    0.50
    Activations Density 0.287%

    No Known Activations