© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15633
    Prev
    Next
    INDEX
    Explanations

    terms related to new beginnings or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrWhiteSpace
    -0.69
     InputDecoration
    -0.67
    сылкі
    -0.66
    ethene
    -0.64
    ArgsConstructor
    -0.61
     terecht
    -0.59
     alamu
    -0.59
    prepareStatement
    -0.58
    SharedCtor
    -0.58
    anghai
    -0.57
    POSITIVE LOGITS
     informée
    0.65
     New
    0.59
    新
    0.58
    mergeFrom
    0.58
    的新
    0.57
    ]<<"
    0.52
     nuevo
    0.51
     novo
    0.51
    Новые
    0.51
    在新
    0.51
    Activations Density 0.395%

    No Known Activations