© 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. 31-GEMMASCOPE-RES-16K
    11. 15
    Prev
    Next
    INDEX
    Explanations

    attributes related to product quality and design characteristics

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

    adjectives that describe positive qualities or appealing characteristics (such as modern, sleek, responsive, efficient, catchy, loving, successful).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ujednoznacz
    -0.71
     disambiguazione
    -0.69
     препратки
    -0.67
     EconPapers
    -0.66
    rungsseite
    -0.63
    Personendaten
    -0.59
    $_['
    -0.56
    ViewFeatures
    -0.56
    sizeCache
    -0.56
    NameInMap
    -0.55
    POSITIVE LOGITS
    ,
    0.75
     highly
    0.75
     yet
    0.65
     versatile
    0.61
     elegant
    0.60
     colourful
    0.60
    highly
    0.55
     attractive
    0.54
     powerful
    0.54
     beautiful
    0.54
    Activations Density 1.077%

    No Known Activations