© 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. 35-GEMMASCOPE-RES-16K
    11. 13682
    Prev
    Next
    INDEX
    Explanations

    references to honor or recognition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gröss
    -1.59
     äusser
    -1.57
     grossen
    -1.57
     generalised
    -1.53
     sólo
    -1.50
     heisst
    -1.46
     standardised
    -1.43
     fertiliser
    -1.42
     tumour
    -1.41
     optimisation
    -1.41
    POSITIVE LOGITS
     enggak
    1.18
     creș
    1.17
     أيضاً
    1.13
     ๆ
    1.11
     și
    1.05
     ști
    1.02
     maș
    0.99
     Daß
    0.99
     uș
    0.97
     ț
    0.94
    Activations Density 0.793%

    No Known Activations