© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and judicial processes

    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
    AndEndTag
    -0.38
    luß
    -0.37
     Pardo
    -0.36
    ɵɵelement
    -0.33
    CppMethod
    -0.32
    Tazama
    -0.32
    Quy
    -0.32
    zydent
    -0.31
     súb
    -0.31
    сшта
    -0.31
    POSITIVE LOGITS
     alternative
    3.77
    alternative
    3.39
     alternate
    3.30
     Alternative
    3.27
    Alternative
    3.25
     alternatives
    3.19
     alternativa
    3.13
     alternatif
    3.13
     ALTERNATIVE
    3.11
     alternativo
    3.02
    Activations Density 1.001%

    No Known Activations