© 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. 40-GEMMASCOPE-RES-16K
    11. 5825
    Prev
    Next
    INDEX
    Explanations

    references to leadership and control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.83
    WebElementEntity
    -0.68
    adaptiveStyles
    -0.65
     betweenstory
    -0.63
    ésultats
    -0.61
     ſch
    -0.61
     ſont
    -0.60
     Geiſt
    -0.59
     témoig
    -0.58
     propOrder
    -0.58
    POSITIVE LOGITS
    r
    0.73
    c
    0.69
    m
    0.69
    d
    0.68
    t
    0.64
    e
    0.64
    n
    0.64
    l
    0.62
    h
    0.61
    w
    0.60
    Activations Density 0.653%

    No Known Activations