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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8057
    Prev
    Next
    INDEX
    Explanations

    references to software packages and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java-related code or file paths

    np_acts-logits-general · gemini-2.0-flash

    java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.54
    setupUi
    -0.53
    contentLoaded
    -0.51
    viewDidLoad
    -0.51
    GTCX
    -0.48
    PreferredItem
    -0.47
     StatefulWidget
    -0.47
    Eloquent
    -0.47
    DebuggerNonUser
    -0.47
     '__
    -0.46
    POSITIVE LOGITS
     JVM
    0.83
     java
    0.83
     Java
    0.83
    java
    0.79
    Java
    0.76
     bean
    0.74
     beans
    0.73
    JDK
    0.73
     JDK
    0.72
     JAXB
    0.69
    Activations Density 2.324%

    No Known Activations