© 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. 10860
    Prev
    Next
    INDEX
    Explanations

    references to education, social issues, and economic disparities

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

    preceding modal verbs or auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    states of being or things possessed

    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
     occur
    -0.50
    Hentet
    -0.49
     culminated
    -0.42
     abound
    -0.42
     exist
    -0.41
    Πηγές
    -0.41
     surfaced
    -0.41
     correspond
    -0.40
     occurred
    -0.40
     OFDb
    -0.40
    POSITIVE LOGITS
     knows
    1.04
     understands
    0.85
     knew
    0.84
    knows
    0.84
     wants
    0.83
     thinks
    0.82
     merasa
    0.80
     prefers
    0.77
     realizes
    0.74
     believes
    0.73
    Activations Density 0.992%

    No Known Activations