© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    elements related to coding or programming contexts, specifically focusing on syntax and structures commonly found in code

    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
    
    -0.60
    oa̍t
    -0.59
     Мексичка
    -0.52
     kaarangay
    -0.51
    OGND
    -0.47
     EconPapers
    -0.47
    InputBorder
    -0.46
    
    -0.46
    __*/
    -0.46
    ✭✭
    -0.46
    POSITIVE LOGITS
    .
    2.14
    ._
    0.91
    .(
    0.82
    .{
    0.81
    .~
    0.75
    .-
    0.75
    .,
    0.72
    .*
    0.72
    .$
    0.71
    .#
    0.69
    Activations Density 5.855%

    No Known Activations