© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    phrases related to selection processes and feature evaluation in contexts like technology and research

    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
    setVerticalGroup
    -0.45
    verwijspagina
    -0.43
    FormTagHelper
    -0.42
    contentLoaded
    -0.38
     Consulta
    -0.38
     propOrder
    -0.37
    LEncoder
    -0.37
    Distribuzione
    -0.36
     TextAppearance
    -0.36
    ButtonItem
    -0.36
    POSITIVE LOGITS
     narrowed
    1.37
     weeding
    1.36
     narrowing
    1.28
     narrows
    1.26
     filtering
    1.21
     screening
    1.18
    Narrow
    1.18
     vet
    1.17
    筛选
    1.15
     sift
    1.15
    Activations Density 1.090%

    No Known Activations