© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12348
    Prev
    Next
    INDEX
    Explanations

    terms related to data partitioning and manipulation processes

    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
     disambiguazione
    -0.77
    transQ
    -0.70
    NameInMap
    -0.70
    ChildScrollView
    -0.62
    
    -0.58
     otomatig
    -0.58
    OGND
    -0.57
    AddTagHelper
    -0.56
    TokenNameLBRACE
    -0.55
    tonsoft
    -0.53
    POSITIVE LOGITS
    🏻
    0.91
    🏼
    0.85
    🏾
    0.82
    🏽
    0.82
    🏿
    0.73
    ters
    0.73
    ted
    0.68
    ting
    0.58
    tting
    0.52
    ned
    0.52
    Activations Density 0.511%

    No Known Activations