© 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. 37-GEMMASCOPE-RES-16K
    11. 5628
    Prev
    Next
    INDEX
    Explanations

    references to articles and their attributes within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.54
     '\\;'
    -0.49
    تقاوى
    -0.44
     hObject
    -0.43
    NgModule
    -0.40
    Спољашње
    -0.40
    principalTable
    -0.39
    ConstraintMaker
    -0.39
    Ծանոթ
    -0.39
     /\.
    -0.38
    POSITIVE LOGITS
     courtesy
    1.33
     adapted
    1.29
    courtesy
    1.13
     Adapted
    1.09
    adapted
    1.07
     Courtesy
    1.06
     reprinted
    1.05
     taken
    1.04
     cortesía
    1.02
     excer
    1.00
    Activations Density 0.626%

    No Known Activations