© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2597
    Prev
    Next
    INDEX
    Explanations

    terms related to trees and their ecological measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.55
     viewHolder
    -0.52
    lido
    -0.49
    trino
    -0.48
    GeneratedCode
    -0.46
     Purse
    -0.45
    tabPage
    -0.45
    脚注の使い方
    -0.45
    protoimpl
    -0.43
    iorno
    -0.42
    POSITIVE LOGITS
     trees
    1.30
     Trees
    1.16
    Trees
    1.08
     TREES
    1.05
     tree
    0.98
    trees
    0.97
     Bäume
    0.94
     arbres
    0.89
     TREE
    0.87
     alberi
    0.84
    Activations Density 0.177%

    No Known Activations