© 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. 20-GEMMASCOPE-RES-16K
    6. 1619
    Prev
    Next
    INDEX
    Explanations

    terms related to trees and their ecological functions

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

    scientific descriptions of trees and their ecological characteristics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    TypedDataSet
    -0.50
     AssemblyProduct
    -0.47
     ویکی‌پدیای
    -0.46
     ν
    -0.43
    InstrumentedTest
    -0.40
    ↹
    -0.40
     Nürnberg
    -0.40
    urlencoded
    -0.40
     propOrder
    -0.39
     FER
    -0.39
    POSITIVE LOGITS
     trees
    0.96
     Trees
    0.87
     tree
    0.78
    trees
    0.77
    Trees
    0.71
     Tree
    0.68
     drze
    0.66
     árboles
    0.65
     TREES
    0.64
     ağaç
    0.63
    Activations Density 0.152%

    No Known Activations