© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1651
    Prev
    Next
    INDEX
    Explanations

    references to plants and their characteristics

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

    plants

    np_acts-logits-general · gemini-2.0-flash

    plant and its scientific context

    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
     autorytatywna
    -0.64
     հղումներ
    -0.60
     kaarangay
    -0.58
    hio
    -0.56
     tartalomajánló
    -0.55
     nahilalakip
    -0.54
     Arias
    -0.53
     يتيمه
    -0.52
     Überblick
    -0.52
    StoryboardSegue
    -0.52
    POSITIVE LOGITS
    Plant
    0.99
     Plant
    0.93
    plant
    0.89
    Plants
    0.88
     plant
    0.82
     PLANT
    0.81
     Plants
    0.80
    PLANT
    0.78
     plants
    0.73
    plants
    0.72
    Activations Density 0.171%

    No Known Activations