© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5555
    Prev
    Next
    INDEX
    Explanations

    quantitative and spatial information related to land and environmental management

    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
     typelib
    -0.59
    -------------</
    -0.57
     NSCoder
    -0.57
    NameInMap
    -0.54
     jspb
    -0.52
    oneofs
    -0.52
     okuyayım
    -0.52
    outWeight
    -0.49
    twimg
    -0.47
    ViewInit
    -0.47
    POSITIVE LOGITS
     acres
    1.36
     hectares
    1.16
     acre
    1.16
     hectare
    1.07
    acre
    1.01
    acres
    0.98
     hectáreas
    0.96
     Acres
    0.93
    hecta
    0.92
    Acres
    0.90
    Activations Density 0.216%

    No Known Activations