© 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. 38-GEMMASCOPE-RES-16K
    11. 13265
    Prev
    Next
    INDEX
    Explanations

    instances of the word "have" and variations related to possession or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.50
    BagConstraints
    -0.47
    pertino
    -0.45
    featureID
    -0.43
     defaultstate
    -0.40
    FromNib
    -0.39
     iſt
    -0.38
    
    -0.37
    msgTypes
    -0.37
     ListTile
    -0.37
    POSITIVE LOGITS
     fun
    3.25
    fun
    2.66
    Fun
    2.39
     Fun
    2.36
     FUN
    2.28
    FUN
    2.02
     diversión
    1.77
     Spaß
    1.76
     divertido
    1.69
     divertidos
    1.50
    Activations Density 0.202%

    No Known Activations