© 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. 34-GEMMASCOPE-RES-16K
    11. 10819
    Prev
    Next
    INDEX
    Explanations

    botanical terms related to plant species in woodland environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.99
    ########.
    -0.97
     EconPapers
    -0.96
     disambiguazione
    -0.94
     otomatig
    -0.90
     utafitiHapana
    -0.89
    GEBURTSDATUM
    -0.84
    Autoritní
    -0.82
    ſelves
    -0.79
    хьтан
    -0.78
    POSITIVE LOGITS
     field
    0.32
     Wiesen
    0.31
     
    0.28
     Europe
    0.27
     card
    0.26
     European
    0.26
     ucran
    0.26
     dan
    0.26
     nisso
    0.25
     circuit
    0.25
    Activations Density 0.298%

    No Known Activations