© 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. 1-GEMMASCOPE-RES-16K
    11. 3302
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and identifiers related to data structures or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    -0.52
     Ti
    -0.51
     Т
    -0.49
     TR
    -0.48
     Ta
    -0.47
     ti
    -0.46
     Tir
    -0.45
     ティ
    -0.45
     ट
    -0.45
     TH
    -0.44
    POSITIVE LOGITS
    table
    1.03
    ters
    0.98
    ten
    0.98
    tem
    0.97
    tam
    0.94
    ter
    0.94
    tab
    0.93
    tad
    0.93
    ted
    0.92
    tet
    0.91
    Activations Density 0.615%

    No Known Activations