© 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. 31-GEMMASCOPE-RES-16K
    11. 8228
    Prev
    Next
    INDEX
    Explanations

    references to hierarchy and expertise, particularly the concept of 'master'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "master" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Grüsse
    -0.42
     mourut
    -0.42
    insatz
    -0.41
    Conclusão
    -0.38
     Wikiseite
    -0.37
     manžel
    -0.37
     Petrol
    -0.36
     ayakkab
    -0.36
     kautta
    -0.36
     kontaktu
    -0.35
    POSITIVE LOGITS
     Master
    1.11
     master
    1.04
     MASTER
    1.03
    Master
    0.94
    master
    0.80
     Masters
    0.77
     masters
    0.77
    MASTER
    0.74
    Masters
    0.73
     マスター
    0.70
    Activations Density 0.050%

    No Known Activations