© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4023
    Prev
    Next
    INDEX
    Explanations

    actions and interactions related to people returning or moving in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     égard
    -0.43
    Халык
    -0.43
    Parameteri
    -0.42
    Ingestion
    -0.40
    fillType
    -0.39
     Diciembre
    -0.39
    hljs
    -0.38
    illai
    -0.38
     feux
    -0.36
    流れ
    -0.36
    POSITIVE LOGITS
    StoryboardSegue
    0.89
    Tembelea
    0.75
     outside
    0.68
    tagHelperRunner
    0.68
    Искәрмәләр
    0.67
    .*")]
    0.67
     errand
    0.67
     BoxFit
    0.66
    InjectAttribute
    0.66
     Wicidata
    0.65
    Activations Density 0.393%

    No Known Activations