© 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. 39-GEMMASCOPE-RES-16K
    11. 1118
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discorso
    -0.39
    ksikon
    -0.39
     الحديث
    -0.38
     anlat
    -0.38
     NgModule
    -0.37
     рассказа
    -0.37
    宣言
    -0.37
    営
    -0.37
    úrese
    -0.36
     createSprite
    -0.36
    POSITIVE LOGITS
     posed
    1.11
     asked
    0.90
     answered
    0.82
     raised
    0.79
    asked
    0.75
    Answered
    0.67
     gestellt
    0.66
     unanswered
    0.66
     Answered
    0.66
     asker
    0.65
    Activations Density 0.247%

    No Known Activations