© 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. 7945
    Prev
    Next
    INDEX
    Explanations

    elements related to legal or formal documentation

    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
    ReusableCell
    -0.27
     adel
    -0.24
                    
    -0.24
    mergeFrom
    -0.23
     ing
    -0.23
     дописавши
    -0.23
    aporation
    -0.23
     Autorisations
    -0.23
     Meksiku
    -0.23
    Kariera
    -0.22
    POSITIVE LOGITS
     nine
    1.74
     Nine
    1.68
     NINE
    1.50
    9
    1.48
    Nine
    1.45
     nueve
    1.42
     ninth
    1.41
     девя
    1.38
     Ninth
    1.38
    nine
    1.37
    Activations Density 3.144%

    No Known Activations