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 - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12981
    Prev
    Next
    INDEX
    Explanations

    conditional statements and requirements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -1.02
     Majefty
    -0.91
    RegressionTest
    -0.91
     Theſe
    -0.88
    LabelTagHelper
    -0.87
    bbene
    -0.85
     purpoſe
    -0.84
     itſelf
    -0.81
    SharedDtor
    -0.80
     ویکی‌پدی
    -0.79
    POSITIVE LOGITS
     الاطلاع
    0.52
    ResponseWriter
    0.49
    <bos>
    0.48
    مصادر
    0.48
     viewDidLoad
    0.45
    ↵↵
    0.43
    complexType
    0.42
    Pyx
    0.41
    
    0.41
    Referencies
    0.40
    Activations Density 0.070%

    No Known Activations