© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1066
    Prev
    Next
    INDEX
    Explanations

    references to datasets and data-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consac
    -0.52
    insegna
    -0.51
     createSprite
    -0.44
    BETWEEN
    -0.43
     CGRectMake
    -0.42
    omotor
    -0.41
    CGRectMake
    -0.41
    颜
    -0.41
    췄
    -0.41
     pengembangan
    -0.40
    POSITIVE LOGITS
     dataset
    1.04
     data
    0.94
     Dataset
    0.92
     datasets
    0.91
     Datasets
    0.82
    errHandler
    0.80
    数据集
    0.79
    数据的
    0.75
    ioutil
    0.75
    Dataset
    0.74
    Activations Density 1.307%

    No Known Activations