© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7862
    Prev
    Next
    INDEX
    Explanations

    phrases related to military training and service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.33
     nakalista
    -0.27
    dflare
    -0.27
     ameste
    -0.27
     verzichten
    -0.27
    Collegamenti
    -0.27
     verwijderen
    -0.26
    Referencoj
    -0.26
    approche
    -0.26
    rungsseite
    -0.26
    POSITIVE LOGITS
     training
    4.03
     Training
    3.50
    Training
    3.44
    training
    3.42
     TRAINING
    3.33
    TRAINING
    3.00
     trainings
    2.91
     Trainings
    2.73
    训练
    2.66
     trained
    2.61
    Activations Density 0.747%

    No Known Activations