© 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. 33-GEMMASCOPE-RES-16K
    11. 8142
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terms related to probabilities and conditions in statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.56
    Personensuche
    -0.54
    AddTagHelper
    -0.48
    richTextPanel
    -0.48
    ThroughAttribute
    -0.46
     ddelweddau
    -0.44
     lenker
    -0.44
     arşivlendi
    -0.43
    useNewUrlParser
    -0.41
     وتسجيلات
    -0.41
    POSITIVE LOGITS
     greater
    1.05
     equal
    0.99
     larger
    0.93
     smaller
    0.90
     groter
    0.86
    greater
    0.83
     bigger
    0.78
     zero
    0.77
     Larger
    0.75
     Smaller
    0.75
    Activations Density 1.932%

    No Known Activations