© 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. 34-GEMMASCOPE-RES-16K
    11. 11577
    Prev
    Next
    INDEX
    Explanations

    technical references to APIs and their versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.57
     للمعارف
    -0.48
    әрмәләр
    -0.43
    ftagPool
    -0.43
    ⤹
    -0.40
    躇
    -0.40
     Brought
    -0.40
    AntiForgeryToken
    -0.39
     StatefulWidget
    -0.38
    렷
    -0.38
    POSITIVE LOGITS
     Api
    0.47
    ApiModelProperty
    0.44
     resourceCulture
    0.43
     AspNetCore
    0.43
     confidentialité
    0.42
     EconPapers
    0.42
     llaves
    0.41
    :✨
    0.40
     endpoint
    0.39
     GIPHY
    0.38
    Activations Density 0.114%

    No Known Activations