© 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. 1198
    Prev
    Next
    INDEX
    Explanations

    keywords and expressions related to programming and coding functions

    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
     ModelExpression
    -0.60
    posedge
    -0.50
    IsContent
    -0.46
    utnik
    -0.45
    はじめに
    -0.41
     propOrder
    -0.41
    dafx
    -0.41
    ContentAsync
    -0.41
     ujednoznacz
    -0.39
    IBOutlet
    -0.39
    POSITIVE LOGITS
    fundamental
    0.45
    AxisAlignment
    0.45
    Regular
    0.41
    semi
    0.41
    Abit
    0.40
     HasFactory
    0.40
    hif
    0.40
     Regular
    0.40
    !***
    0.40
    quelize
    0.40
    Activations Density 0.131%

    No Known Activations