© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    code-related references and library usages, particularly focusing on input/output operations and data handling

    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
     nonUne
    -0.52
    gsSP
    -0.50
    جوايز
    -0.50
     Wicidata
    -0.49
    >*/
    -0.48
    protoc
    -0.48
    
    -0.47
    Crédit
    -0.47
     Weeknd
    -0.47
     Numerade
    -0.47
    POSITIVE LOGITS
     taxi
    0.51
    Taxi
    0.50
    Scanner
    0.49
     Taxi
    0.48
     dial
    0.48
    dial
    0.47
    ParallelGroup
    0.47
    taxi
    0.45
     lightning
    0.44
    IAL
    0.42
    Activations Density 1.330%

    No Known Activations