© 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. 6101
    Prev
    Next
    INDEX
    Explanations

    references to individuals' military service and their loyalty to either the Union or Confederate side during the Civil War

    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
     behavioural
    -0.74
     colourful
    -0.71
     Behavioural
    -0.69
     woken
    -0.68
     maximise
    -0.68
     kasarigan
    -0.67
     BEHAV
    -0.65
    colourful
    -0.62
    LEGGI
    -0.60
    behaviour
    -0.59
    POSITIVE LOGITS
     caráter
    0.52
    expandindo
    0.52
    dafx
    0.47
     employes
    0.45
     employés
    0.45
     auffi
    0.42
    enumii
    0.42
     indor
    0.41
     Shakspeare
    0.40
     pecuni
    0.39
    Activations Density 1.249%

    No Known Activations