© 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. 9194
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and summations related to sequences

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

    mathematical summation notation with subscripts and indices in LaTeX format.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     infan
    -0.43
    ViewInit
    -0.40
     Савезне
    -0.40
    requestCode
    -0.38
    föra
    -0.37
     FileReader
    -0.37
    SPJ
    -0.36
    SaveChangesAsync
    -0.36
    ésor
    -0.36
     tänka
    -0.35
    POSITIVE LOGITS
    httphttps
    0.58
     protoimpl
    0.57
    substack
    0.52
    fjspx
    0.50
     שוליים
    0.49
    ScopeManager
    0.49
    hésitez
    0.48
    ➟
    0.48
     Paglinawan
    0.48
    SequentialGroup
    0.47
    Activations Density 0.710%

    No Known Activations