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

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 13859
    Prev
    Next
    INDEX
    Explanations

    variable and parameter names commonly used in mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.59
    twimg
    -0.51
    KEYCODE
    -0.49
    ModelSerializer
    -0.49
    WebVitals
    -0.49
    Vidite
    -0.49
    gatsby
    -0.48
    IsMutable
    -0.47
    SharedDtor
    -0.47
    scar
    -0.46
    POSITIVE LOGITS
    msubsup
    0.75
     kasarigan
    0.46
    awtextra
    0.39
    mű
    0.37
    ientí
    0.36
     확인함
    0.36
     frumos
    0.35
    
    0.35
    GEBURTS
    0.34
    บัติ
    0.33
    Activations Density 1.263%

    No Known Activations