© 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. 2-GEMMASCOPE-RES-16K
    11. 15800
    Prev
    Next
    INDEX
    Explanations

    references to the concept of living spaces or homes

    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
     дописавши
    -0.73
     Northam
    -0.64
     ModelExpression
    -0.63
     skunk
    -0.62
     esboço
    -0.61
     judiciales
    -0.61
     indicando
    -0.61
     collègues
    -0.60
     reembols
    -0.60
     feminists
    -0.60
    POSITIVE LOGITS
     living
    4.18
     Living
    3.74
    living
    3.65
    Living
    3.61
     LIVING
    3.44
    LIVING
    3.21
     lived
    2.34
     live
    2.09
     vivir
    2.04
     vivant
    2.04
    Activations Density 0.072%

    No Known Activations