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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15255
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.68
    
    -0.66
    WTS
    -0.66
    InitVars
    -0.66
     وتسجيلات
    -0.65
    MatButtonModule
    -0.64
    sizeCache
    -0.64
     KeyEvent
    -0.63
     EClass
    -0.61
    ValueStyle
    -0.60
    POSITIVE LOGITS
     Möglich
    0.80
     pleaſure
    0.79
     ſeveral
    0.78
    ſelves
    0.75
     Chriftian
    0.72
     ſmall
    0.71
     оригіналу
    0.71
     Majefty
    0.71
     Apostolic
    0.69
     Diſ
    0.69
    Activations Density 0.101%

    No Known Activations