© 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. 31-GEMMASCOPE-RES-16K
    11. 2704
    Prev
    Next
    INDEX
    Explanations

    elements related to rulers and governance

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

    ancient or historical references, particularly to rulers, dynasties, mythological figures, and classical civilizations.

    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
    AndEndTag
    -0.56
     cref
    -0.50
     Arabic
    -0.48
    limus
    -0.48
     تضيفلها
    -0.47
     Arab
    -0.46
     Elizabethan
    -0.45
     Islamic
    -0.42
    oglio
    -0.42
     Roman
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.46
    rungsseite
    0.40
    ագրություններ
    0.40
     estekak
    0.39
     disambiguazione
    0.39
    UnusedPrivate
    0.38
     sacrificio
    0.37
     שוליים
    0.37
     sacrific
    0.37
     poveznice
    0.36
    Activations Density 0.146%

    No Known Activations