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. 103081
    Prev
    Next
    INDEX
    Explanations

    programming and software terminology, specifically focusing on code functions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     istrinya
    -0.50
     sanitarias
    -0.50
    makeatother
    -0.48
    erintah
    -0.47
     dezelve
    -0.47
     '{@
    -0.47
    ModelForm
    -0.46
    ğmen
    -0.46
     Voraus
    -0.46
     zoude
    -0.46
    POSITIVE LOGITS
    
    0.76
    Obfuscated
    0.64
    yntaxException
    0.64
    edata
    0.59
    getRuntime
    0.49
     мәкал
    0.49
    uled
    0.49
    verifyException
    0.47
    
    0.44
    dafx
    0.41
    Activations Density 0.002%

    No Known Activations