© 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. 0-GEMMASCOPE-RES-16K
    11. 9463
    Prev
    Next
    INDEX
    Explanations

    properties and relationships within a structured data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.75
     Numerade
    -0.67
     للاسماء
    -0.66
    Espèce
    -0.58
    httphttps
    -0.57
    aarrggbb
    -0.57
     EconPapers
    -0.57
    はじめに
    -0.56
    期刊论文
    -0.56
    :✨
    -0.56
    POSITIVE LOGITS
    prop
    0.85
     prop
    0.75
     custom
    0.72
     PROP
    0.66
     character
    0.66
     props
    0.64
     property
    0.63
    Prop
    0.63
     actor
    0.62
    Props
    0.62
    Activations Density 1.679%

    No Known Activations