© 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. 40-GEMMASCOPE-RES-16K
    11. 5630
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.59
     onOptions
    -0.57
    OGND
    -0.53
     InputDecoration
    -0.46
    rungsseite
    -0.45
     betweenstory
    -0.45
    CppMethod
    -0.44
    ajuato
    -0.42
    appé
    -0.40
    untamiento
    -0.40
    POSITIVE LOGITS
     Pacific
    1.27
    Pacific
    1.09
     Polynesia
    1.02
     pacific
    0.99
     Samoa
    0.97
     Polynesian
    0.96
     PACIFIC
    0.96
     Fiji
    0.94
     Pacífico
    0.93
     Vanuatu
    0.91
    Activations Density 0.324%

    No Known Activations