© 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. 30-GEMMASCOPE-RES-16K
    11. 12526
    Prev
    Next
    INDEX
    Explanations

    authors and their achievements within the realm of literature, particularly focusing on dark fiction

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

    Indicates an author or writer

    np_acts-logits-general · gemini-2.0-flash

    author producing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informe
    -0.44
     Wearing
    -0.43
    Wearing
    -0.41
     trous
    -0.39
    informe
    -0.39
     Negotiation
    -0.38
    Véxase
    -0.38
    acting
    -0.37
    ticon
    -0.35
    beforeAll
    -0.35
    POSITIVE LOGITS
     producing
    1.03
     produces
    0.94
     produce
    0.87
     producir
    0.83
     Producing
    0.81
    Producing
    0.77
    producing
    0.76
     produire
    0.75
     produzir
    0.75
     creating
    0.72
    Activations Density 0.519%

    No Known Activations