© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12334
    Prev
    Next
    INDEX
    Explanations

    characters, symbols, and mathematical or programming notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuffs
    -0.48
    zzleHttp
    -0.48
     husbands
    -0.48
    rawDesc
    -0.47
     battles
    -0.46
     vendors
    -0.45
     utafitiHapana
    -0.45
     tumours
    -0.44
    Lifecycle
    -0.44
    sprogramm
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.40
    transQ
    0.39
    izarse
    0.35
     mostrarse
    0.34
     istore
    0.34
    empêcher
    0.34
     acompañar
    0.33
     siitä
    0.32
    قایناق‌لار
    0.32
     adaptarse
    0.32
    Activations Density 1.476%

    No Known Activations