© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6250
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations or treatments within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or scientific expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical or academic terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     Mal
    -0.35
     mal
    -0.34
     cou
    -0.32
    ỉ
    -0.31
     confusion
    -0.31
     Dars
    -0.30
     fundamental
    -0.29
     فت
    -0.29
     Elect
    -0.29
     cargos
    -0.29
    POSITIVE LOGITS
    [toxicity=0]
    1.16
    httphttps
    0.77
    Diweddarwch
    0.76
     ujednoznacz
    0.73
    
    0.73
    webElementXpaths
    0.72
    TypedDataSet
    0.70
     informée
    0.70
    期刊论文
    0.68
    expandindo
    0.67
    Activations Density 2.182%

    No Known Activations