© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11570
    Prev
    Next
    INDEX
    Explanations

    temporal markers or phrases indicating time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PDI
    -0.68
     CRI
    -0.65
     PSM
    -0.62
     NTB
    -0.60
     CTS
    -0.60
     PPD
    -0.60
     Италијани
    -0.60
     SST
    -0.60
     PHA
    -0.60
    alians
    -0.59
    POSITIVE LOGITS
    During
    0.49
    addPreferredGap
    0.46
     During
    0.46
     At
    0.44
    Upon
    0.43
     On
    0.43
    At
    0.42
     Upon
    0.42
    On
    0.42
     illustrationer
    0.40
    Activations Density 0.927%

    No Known Activations