Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73618
    Prev
    Next
    INDEX
    Explanations

    mentions of biochemical processes and research findings

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

    Technical terminology and specialized vocabulary from various domains including pharmaceuticals, computing, diplomacy, and scientific literature.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SaveChangesAsync
    -0.47
     otomatig
    -0.47
    jsxFileName
    -0.47
    Хьажоргаш
    -0.45
    WillAppear
    -0.44
     kasarigan
    -0.44
     незавершена
    -0.40
    PerformLayout
    -0.40
     uLocal
    -0.39
     totalSupply
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.59
    AddTagHelper
    0.54
    AlterField
    0.50
    AndroidJUnit
    0.48
    ⓧ
    0.48
    RegressionTest
    0.47
    Tikang
    0.47
     resourceCulture
    0.43
    onAttach
    0.42
     AssemblyCompany
    0.41
    Activations Density 23.601%

    No Known Activations