© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious beliefs and discussions about their implications

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

    prepositions and function words that connect nouns and concepts in formal or religious discourse.

    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
     aforementioned
    -0.63
     moniker
    -0.61
     critters
    -0.60
     lyre
    -0.57
     entirety
    -0.56
     paparazzi
    -0.56
     bridesmaid
    -0.56
     prioriti
    -0.54
     premise
    -0.54
     demographics
    -0.54
    POSITIVE LOGITS
    請繼續往下閱讀
    0.49
    ้งาน
    0.45
    SequentialGroup
    0.45
    GraphicsUnit
    0.45
    そういう
    0.44
    UrlResolution
    0.43
     genü
    0.39
    原始内容存档
    0.39
     such
    0.39
     Miß
    0.38
    Activations Density 0.957%

    No Known Activations