© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12141
    Prev
    Next
    INDEX
    Explanations

    structural elements of narratives, such as plots and character arcs

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

    story, movie, series, tale, strip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Datuak
    -0.54
    WireFormatLite
    -0.52
     Italijani
    -0.51
    RectangleBorder
    -0.51
     Taktlose
    -0.49
     oprot
    -0.47
    Vidite
    -0.45
     Obrador
    -0.44
    XmlElement
    -0.43
    stateMutability
    -0.43
    POSITIVE LOGITS
     story
    1.00
    讲述
    0.81
     tale
    0.80
     follows
    0.73
     revolves
    0.72
     raconte
    0.71
     stories
    0.71
    story
    0.68
    故事
    0.68
     داستان
    0.67
    Activations Density 0.040%

    No Known Activations