© 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. 3-GEMMASCOPE-RES-16K
    11. 9020
    Prev
    Next
    INDEX
    Explanations

    references to the structure of data in programming contexts, particularly focusing on rows and columns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLR
    -0.57
    SharedCtor
    -0.57
     mapStateToProps
    -0.52
     peer
    -0.52
     Мексичка
    -0.50
     feit
    -0.50
    peer
    -0.50
    extra
    -0.49
     لينك
    -0.49
    posedge
    -0.48
    POSITIVE LOGITS
    Rows
    0.89
    rows
    0.87
     rows
    0.81
     roles
    0.77
     Roles
    0.73
    Tasks
    0.70
     Rows
    0.68
    Roles
    0.68
     tasks
    0.67
    roles
    0.60
    Activations Density 0.066%

    No Known Activations