© 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. 12323
    Prev
    Next
    INDEX
    Explanations

    phrases related to following or tracking actions and events

    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
     following
    -0.58
     chande
    -0.46
    AntiForgeryToken
    -0.39
     AssemblyVersion
    -0.39
    arcoma
    -0.39
     للاسماء
    -0.38
    دانشنامهٔ
    -0.37
    CppMethod
    -0.37
    edb
    -0.37
     следующее
    -0.36
    POSITIVE LOGITS
     suit
    1.05
     closely
    0.79
    suit
    0.74
    Suit
    0.62
     Suit
    0.60
     suite
    0.55
     kautta
    0.54
    suits
    0.53
    actualité
    0.53
     instrucciones
    0.52
    Activations Density 0.208%

    No Known Activations