© 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. 14702
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial transactions and comparisons

    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
     respectively
    -0.38
    tonode
    -0.36
     respective
    -0.33
    Затем
    -0.33
    Portail
    -0.33
    分别
    -0.32
     respectivamente
    -0.32
    respectively
    -0.32
    いくつか
    -0.31
    Sommaire
    -0.31
    POSITIVE LOGITS
     every
    3.80
    every
    3.36
    Every
    3.00
     Every
    2.94
     EVERY
    2.63
     setiap
    2.36
     ogni
    2.33
    EVERY
    2.33
    ทุก
    2.06
     minden
    1.88
    Activations Density 1.049%

    No Known Activations