© 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. 3-GEMMASCOPE-RES-16K
    11. 7912
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to novelty and newness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    canActivate
    -0.52
    énario
    -0.51
    |}{}
    -0.51
    equila
    -0.49
    壌
    -0.46
    AtIndexPath
    -0.44
    ribune
    -0.44
    getValueAt
    -0.44
    ymce
    -0.44
     hemma
    -0.44
    POSITIVE LOGITS
     new
    2.48
    new
    2.30
     nueva
    2.11
     nuevo
    2.11
    新
    2.06
    新的
    2.00
     nuevos
    2.00
     nuevas
    1.93
     nouvelle
    1.92
     NEW
    1.92
    Activations Density 0.324%

    No Known Activations