© 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. 28-GEMMASCOPE-RES-16K
    11. 7969
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimizing processes for efficiency and effectiveness

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

    optimization or achieving maximum results

    np_acts-logits-general · gemini-2.0-flash

    maximum or optimal outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.51
    adaptiveStyles
    -0.49
     فريبيس
    -0.47
    FDRE
    -0.45
    webElementXpaths
    -0.45
    蚪
    -0.45
     wireType
    -0.43
    LEGGI
    -0.42
    いかが
    -0.42
     merk
    -0.42
    POSITIVE LOGITS
     maximize
    1.53
     maximized
    1.38
     maximizes
    1.38
     maximizing
    1.37
     maximise
    1.36
     maxim
    1.33
     maximum
    1.29
     Maximize
    1.25
     optimum
    1.24
     maximal
    1.20
    Activations Density 0.598%

    No Known Activations