© 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. 10-GEMMASCOPE-RES-16K
    11. 3565
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "within" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.77
    O
    -0.71
    cy
    -0.67
     TPS
    -0.66
    io
    -0.64
     pep
    -0.62
     DSC
    -0.61
    She
    -0.61
    He
    -0.60
    lar
    -0.60
    POSITIVE LOGITS
     Within
    1.72
    within
    1.72
    Within
    1.68
     WITHIN
    1.63
     within
    1.62
     InputDecoration
    1.22
     binnen
    1.17
     entro
    1.13
    dentro
    1.06
     innerhalb
    1.05
    Activations Density 0.085%

    No Known Activations