© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13221
    Prev
    Next
    INDEX
    Explanations

    terms related to gene therapy and metabolic processes in cells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Genes, acids, brain, cell, wound

    np_acts-logits-general · gemini-2.0-flash

    biological processes and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umgang
    -0.48
     näky
    -0.47
     enseñ
    -0.46
     Prinzip
    -0.46
     caminh
    -0.46
     pregunt
    -0.45
     humanidade
    -0.45
    protetor
    -0.45
     Beobach
    -0.45
    awtextra
    -0.45
    POSITIVE LOGITS
     dna
    0.53
     Sexual
    0.49
     serotonin
    0.48
     vulcan
    0.47
     directional
    0.46
     Nasal
    0.45
     Missile
    0.45
    clusal
    0.45
     DNS
    0.45
     BoxFit
    0.45
    Activations Density 1.241%

    No Known Activations