© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions and endings

    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
     urząd
    -0.38
    ITARY
    -0.33
    createElement
    -0.32
     hyö
    -0.32
     maître
    -0.32
    zką
    -0.32
     utilice
    -0.31
     wyma
    -0.31
    Cuántos
    -0.30
     zbior
    -0.30
    POSITIVE LOGITS
     виправивши
    0.75
    __":
    0.70
     للمعارف
    0.70
    
    0.63
    __':
    0.62
     ending
    0.62
    AnimationsModule
    0.62
     ended
    0.62
     OMITBAD
    0.60
     Ending
    0.58
    Activations Density 0.256%

    No Known Activations