© 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 EvalsExportsinterp-engineNEWAPI 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. 6622
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to summation and integral calculus

    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
    брь
    -0.37
    parsedMessage
    -0.37
     eccl
    -0.37
     Dör
    -0.35
     Méndez
    -0.35
    RegressionTest
    -0.32
    hygiène
    -0.32
     administrator
    -0.32
     though
    -0.32
     Schild
    -0.32
    POSITIVE LOGITS
    UrlResolution
    0.67
    存于互联网档案馆
    0.60
    ContentLoaded
    0.60
    XmlAccessType
    0.60
    limits
    0.60
    KURZBESCHREIBUNG
    0.56
    帖最后由
    0.53
     limits
    0.50
     EconPapers
    0.48
     noDo
    0.47
    Activations Density 0.808%

    No Known Activations