© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 93192
    Prev
    Next
    INDEX
    Explanations

    details about a specific car model, particularly in the context of auctions or sales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ंदीखरीदारी
    -0.47
    सार
    -0.36
    ThroughAttribute
    -0.34
    "])){
    -0.34
    ༘
    -0.30
    ApplicationTests
    -0.30
     authors
    -0.29
    ])){
    -0.29
     silently
    -0.29
     mixed
    -0.28
    POSITIVE LOGITS
    adaptiveStyles
    0.58
    脚注の使い方
    0.52
     فريبيس
    0.52
    OGND
    0.51
     jspb
    0.49
     ChromeDriver
    0.49
    
    0.48
    addPreferredGap
    0.48
    webElementGuid
    0.48
    Gön
    0.47
    Activations Density 0.010%

    No Known Activations