© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9690
    Prev
    Next
    INDEX
    Explanations

    complex structures or relationships in scientific or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.70
     Waray
    -0.63
    Хьажоргаш
    -0.49
     EconPapers
    -0.48
    DotNetBar
    -0.47
    LLocation
    -0.46
    XMLSchema
    -0.46
    échal
    -0.45
    marle
    -0.45
    eby
    -0.44
    POSITIVE LOGITS
     three
    0.96
     trio
    0.93
     Three
    0.89
     tri
    0.88
    three
    0.88
    Three
    0.84
    三
    0.83
     üç
    0.82
     三
    0.81
     три
    0.81
    Activations Density 1.609%

    No Known Activations