© 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. 13689
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and family ties

    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
     οποίο
    -0.59
     dets
    -0.59
     которое
    -0.56
     welches
    -0.54
     stalo
    -0.52
     themselves
    -0.52
     boyhood
    -0.51
     Оно
    -0.51
     zostało
    -0.50
     koje
    -0.50
    POSITIVE LOGITS
     herself
    2.69
    herself
    2.05
     her
    1.48
     그녀
    1.32
    彼女は
    1.28
     suaminya
    1.28
     hennes
    1.27
    她的
    1.26
    但她
    1.26
    彼女の
    1.23
    Activations Density 0.964%

    No Known Activations