© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    expressions of positive sentiments or feelings of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.50
     Autorizaciones
    -0.44
    ècie
    -0.43
    出版年
    -0.41
    Cyfarwyddwr
    -0.41
     Arkivert
    -0.41
     Italijanski
    -0.40
     voici
    -0.39
     мәкал
    -0.38
    &__
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    0.54
    endphp
    0.50
     gratifying
    0.47
    Прият
    0.45
     Überras
    0.44
     surprising
    0.44
    omitempty
    0.44
    CodeAttribute
    0.44
    addGap
    0.42
     känns
    0.42
    Activations Density 0.339%

    No Known Activations