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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2203
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimental research and findings

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

    experimental and cognitive studies

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Искәрмәләр
    -0.58
    tvguidetime
    -0.55
    ungkinan
    -0.54
    Джерела
    -0.54
    GIVEREF
    -0.54
    UrlResolution
    -0.51
    PDOException
    -0.50
     BrowserModule
    -0.50
     $_"
    -0.50
    EndGlobal
    -0.50
    POSITIVE LOGITS
     psychologists
    0.43
     experiments
    0.39
     Lab
    0.38
     neuroscience
    0.37
     psychologist
    0.37
    研究
    0.36
     experiment
    0.36
     experimenter
    0.35
     research
    0.35
    Lab
    0.35
    Activations Density 0.102%

    No Known Activations