© 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 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. 15113
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" to indicate comparisons or simultaneous actions

    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
     Psyche
    -0.65
    ="@+
    -0.62
    ⓧ
    -0.62
     FUT
    -0.62
    complexType
    -0.60
     profeta
    -0.59
     greateſt
    -0.59
    FieldNumber
    -0.58
    nota
    -0.58
     TextInputType
    -0.58
    POSITIVE LOGITS
    wijl
    0.86
     enquanto
    0.75
     Enquanto
    0.74
     mientras
    0.68
     när
    0.67
     while
    0.67
     gdy
    0.64
     Wikispecies
    0.62
    őd
    0.62
    När
    0.62
    Activations Density 0.131%

    No Known Activations