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. 73563
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers in programming terminology

    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
    .*")]
    -0.65
     &___
    -0.61
     InputDecoration
    -0.60
    ++){
    
    -0.60
    __*/
    -0.60
    RectangleBorder
    -0.60
    ThemeOverlay
    -0.59
    ]")]
    -0.59
    fjspx
    -0.59
    ++){
    -0.58
    POSITIVE LOGITS
     private
    0.51
     ویکی‌پدیای
    0.47
    private
    0.45
     craft
    0.40
     thus
    0.40
     Proud
    0.37
     PRIVATE
    0.37
    yti
    0.36
     proud
    0.36
     noin
    0.36
    Activations Density 0.001%

    No Known Activations