© 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. 31-GEMMASCOPE-RES-16K
    11. 3663
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code elements related to resources and stylesheets

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

    HTML and web framework markup tags with their attributes and file paths.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.70
    parsedMessage
    -0.69
    
    -0.67
     createSlice
    -0.66
    bkz
    -0.64
    Diwedd
    -0.64
    Jereo
    -0.64
    posedge
    -0.62
    ModelAdmin
    -0.61
    omock
    -0.61
    POSITIVE LOGITS
    link
    0.52
     link
    0.51
     ayrıca
    0.46
     LINK
    0.38
    LINK
    0.38
     garantía
    0.35
     Link
    0.33
     inscrição
    0.32
     inoltre
    0.32
     inalámbrica
    0.32
    Activations Density 0.104%

    No Known Activations