© 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. 11406
    Prev
    Next
    INDEX
    Explanations

    declarations of public and static methods or variables in code

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

    Java code syntax and keywords

    np_acts-logits-general · gemini-2.0-flash

    public static keywords

    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
    RegressionTest
    -0.90
     Италијани
    -0.88
     незавершена
    -0.82
     становника
    -0.79
     AppCompatTheme
    -0.79
     betweenstory
    -0.76
     فريبيس
    -0.75
    WriteTagHelper
    -0.74
    bukkit
    -0.74
     springfox
    -0.73
    POSITIVE LOGITS
     static
    1.09
     void
    0.77
     int
    0.67
     async
    0.65
     final
    0.64
     class
    0.64
    )();
    0.61
     readonly
    0.58
     enum
    0.58
     boolean
    0.57
    Activations Density 0.024%

    No Known Activations