© 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. 14664
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases and transitions in discourse

    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
    出版年
    -0.57
     disambiguazione
    -0.51
     &___
    -0.51
     referrerpolicy
    -0.49
    Autoritní
    -0.47
    AutoScaleMode
    -0.46
    Trama
    -0.45
    ingang
    -0.43
     betweenstory
    -0.43
     برانيه
    -0.43
    POSITIVE LOGITS
     above
    2.27
    Above
    2.09
    above
    2.05
     Above
    2.03
     most
    1.75
     acima
    1.73
     ABOVE
    1.68
     przede
    1.45
    most
    1.41
     importantly
    1.41
    Activations Density 0.332%

    No Known Activations