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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5947
    Prev
    Next
    INDEX
    Explanations

    Java interface and class keywords related to event handling and serialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.97
    +#+#
    -0.95
    InjectAttribute
    -0.95
     estimés
    -0.91
    tagHelperRunner
    -0.90
     BoxFit
    -0.89
     noDo
    -0.86
     BorderRadius
    -0.86
     tartalomajánló
    -0.85
    viewDidLoad
    -0.85
    POSITIVE LOGITS
    ActionListener
    1.84
    Serializable
    1.37
     Serializable
    1.27
     referenties
    0.55
     ActionListener
    0.54
    INCREF
    0.53
    mekte
    0.50
    ChangeListener
    0.50
    ↵↵
    0.50
    </h2>
    0.46
    Activations Density 0.011%

    No Known Activations