© 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. 10818
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate being "on track" or "on target" in various contexts

    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
    errHandler
    -0.48
     للمعارف
    -0.47
    ViewInit
    -0.47
    mappedBy
    -0.45
     jScrollPane
    -0.44
    RegressionTest
    -0.44
    FromNib
    -0.43
    حياته
    -0.42
     udział
    -0.42
    الإنجليزية
    -0.41
    POSITIVE LOGITS
     par
    0.68
     track
    0.65
     verge
    0.64
     pace
    0.60
     edge
    0.58
     cusp
    0.56
     precipice
    0.55
     alert
    0.53
     guard
    0.52
     target
    0.51
    Activations Density 0.197%

    No Known Activations