© 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. 9-GEMMASCOPE-RES-16K
    11. 8156
    Prev
    Next
    INDEX
    Explanations

    names of characters, particularly in a cultural or entertainment context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sellado
    -0.54
     guste
    -0.49
     kiin
    -0.45
     pysty
    -0.45
     construit
    -0.45
     hyö
    -0.45
     mahdollis
    -0.44
     scales
    -0.44
     apunt
    -0.43
     esperança
    -0.43
    POSITIVE LOGITS
     nakalista
    0.79
    !*\
    0.68
     незавершена
    0.64
    FormTagHelper
    0.60
    
    0.56
     يتيمه
    0.55
     <=",
    0.55
    Tembelea
    0.55
     endwhile
    0.54
     كومونز
    0.54
    Activations Density 0.154%

    No Known Activations