© 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. 33-GEMMASCOPE-RES-16K
    11. 255
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to vector spaces and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.53
    jsxFileName
    -0.43
    spender
    -0.42
    ffindor
    -0.35
    出版年
    -0.35
    GOTREF
    -0.35
    timent
    -0.35
    навли
    -0.35
    routeProvider
    -0.34
    lehnt
    -0.33
    POSITIVE LOGITS
     map
    1.09
     maps
    1.05
     mapping
    1.04
     mappings
    0.96
     Maps
    0.93
     Map
    0.91
    maps
    0.90
     Mapping
    0.88
    Maps
    0.86
    映射
    0.85
    Activations Density 1.640%

    No Known Activations