© 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. 37-GEMMASCOPE-RES-16K
    6. 735
    Prev
    Next
    INDEX
    Explanations

    references to naval terminology and military operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Púb
    -0.49
     Pública
    -0.45
     esclavos
    -0.42
     sentarse
    -0.42
     delegación
    -0.40
     Construcción
    -0.40
     Público
    -0.40
     navideño
    -0.39
     antemano
    -0.39
     colorear
    -0.39
    POSITIVE LOGITS
     Orion
    0.88
     Apollo
    0.83
     Neptune
    0.82
     Jupiter
    0.81
     Pegasus
    0.81
     Aurora
    0.79
     Phoenix
    0.79
     Horizon
    0.75
     Athena
    0.75
     Zeus
    0.74
    Activations Density 0.702%

    No Known Activations