© 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. 13-GEMMASCOPE-RES-16K
    11. 6729
    Prev
    Next
    INDEX
    Explanations

    SQL commands, specifically variations of the "SELECT" statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bedrijf
    -0.47
    companyName
    -0.45
     createdAt
    -0.45
     middleware
    -0.45
    hou
    -0.45
    ,
    -0.44
     AssemblyCompany
    -0.43
    hour
    -0.43
     alkalinity
    -0.43
     Empresas
    -0.43
    POSITIVE LOGITS
     select
    1.39
     Select
    1.33
    select
    1.30
     selected
    1.29
     Selection
    1.25
    Select
    1.24
     selection
    1.23
     SELECT
    1.23
     selects
    1.19
    SELECT
    1.18
    Activations Density 0.111%

    No Known Activations