© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15702
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to molecular spectroscopy and dynamics

    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
     Reef
    -0.36
    候
    -0.34
    SerializedSize
    -0.34
     Frie
    -0.34
     scin
    -0.33
     <<<<<<<<<<<<<<
    -0.33
     ATX
    -0.32
     betta
    -0.31
    ATX
    -0.31
     voice
    -0.31
    POSITIVE LOGITS
     vibrational
    0.75
     molecule
    0.69
     stretching
    0.65
     molé
    0.65
     molecular
    0.64
     Stretching
    0.63
    molecule
    0.62
     molecules
    0.61
     IR
    0.60
     infrared
    0.59
    Activations Density 0.718%

    No Known Activations