© 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. 11775
    Prev
    Next
    INDEX
    Explanations

    code imports in Java

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

    Java imports or packages

    np_acts-logits-general · gemini-2.0-flash

    java import statements

    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
     raiſ
    -0.86
     NUKAT
    -0.86
     ddelweddau
    -0.84
     uſed
    -0.82
     Anſ
    -0.79
     jsPsych
    -0.77
    CloseOperation
    -0.76
     ſtate
    -0.76
    SBATCH
    -0.76
     Monfieur
    -0.76
    POSITIVE LOGITS
     java
    0.65
    import
    0.60
    <eos>
    0.57
    java
    0.49
    ${
    0.48
    org
    0.48
    RenderAtEndOf
    0.47
     com
    0.46
    ↵
    0.46
     So
    0.45
    Activations Density 0.083%

    No Known Activations