© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29342
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins involved in biological processes

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

    words starting with "tre"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MIPS
    -0.81
     Cuth
    -0.76
    ing
    -0.74
    Czytaj
    -0.73
    qtype
    -0.72
    źródło
    -0.71
    aspectj
    -0.70
     Lass
    -0.69
     poff
    -0.69
    ppincott
    -0.69
    POSITIVE LOGITS
     Tre
    1.17
    Tre
    1.16
    tre
    1.12
     TRE
    1.08
    TRE
    1.02
    Trev
    0.90
     tre
    0.90
    fre
    0.87
    Gre
    0.82
     Trek
    0.81
    Activations Density 0.041%

    No Known Activations