© 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. 0-GEMMASCOPE-RES-16K
    11. 10332
    Prev
    Next
    INDEX
    Explanations

    technical attributes and configurations related to software assemblies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RoomId
    -0.94
    TaskId
    -0.92
    clerView
    -0.91
    bibfield
    -0.91
    ItemName
    -0.90
    ByDate
    -0.88
    UserList
    -0.88
    CustomerId
    -0.87
    GroupId
    -0.86
    ProductId
    -0.85
    POSITIVE LOGITS
     CreateTagHelper
    3.36
    LookAnd
    3.25
    Personendaten
    3.22
     autorytatywna
    3.19
     propOrder
    3.17
    tagHelperRunner
    3.09
    sizeCache
    3.08
     AssemblyCulture
    3.06
     EconPapers
    3.06
    AddTagHelper
    3.05
    Activations Density 2.926%

    No Known Activations