© 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. 36-GEMMASCOPE-RES-16K
    11. 7632
    Prev
    Next
    INDEX
    Explanations

    variations of the word "set" and other related actions and states

    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
    abestanden
    -0.52
    StoryboardSegue
    -0.47
    encodeWith
    -0.45
    RegressionTest
    -0.43
    ကိုးကား
    -0.40
     صوتيه
    -0.38
     ControllerBase
    -0.38
    Externí
    -0.38
    crollView
    -0.37
    RegistryLite
    -0.36
    POSITIVE LOGITS
     Up
    1.84
     ups
    1.84
    UP
    1.81
    up
    1.81
     UP
    1.80
    Up
    1.77
    ups
    1.68
     Ups
    1.63
    Ups
    1.55
     up
    1.51
    Activations Density 0.507%

    No Known Activations