© 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. 10255
    Prev
    Next
    INDEX
    Explanations

    emotional descriptors or adjectives related to characters and situations

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

    positive descriptive adjectives used to characterize people, ideas, or experiences.

    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
    CrossRef
    -0.56
    WritableDatabase
    -0.55
    はじめに
    -0.53
     Meksiku
    -0.53
    請繼續往下閱讀
    -0.50
     rangka
    -0.49
     nahilalakip
    -0.48
    RegistryLite
    -0.48
    出版年
    -0.47
     himo
    -0.47
    POSITIVE LOGITS
     affair
    0.68
     thing
    0.67
     addition
    0.66
     beast
    0.59
     example
    0.58
     proposition
    0.57
     phenomenon
    0.55
     choice
    0.53
     piece
    0.53
     part
    0.51
    Activations Density 0.302%

    No Known Activations