© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    phrases related to enhancing experiences with a touch of creativity and elegance

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

    phrases describing elegant or refined qualities being added to enhance something's appearance or character.

    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
     للمعارف
    -0.66
    rungsseite
    -0.62
    verwijspagina
    -0.58
     utafitiHapana
    -0.54
    heitsbild
    -0.54
    onedDateTime
    -0.52
    IBAction
    -0.51
    曖昧さ回避
    -0.51
    TagMode
    -0.50
    Clik
    -0.50
    POSITIVE LOGITS
     flavor
    0.81
     charm
    0.76
     flavour
    0.74
     tinge
    0.72
     sparkle
    0.70
    flavor
    0.66
     spice
    0.65
     elements
    0.64
     flair
    0.64
     hint
    0.61
    Activations Density 0.318%

    No Known Activations