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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 862
    Prev
    Next
    INDEX
    Explanations

    code statements defining classes and their attributes

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

    C++ or Java class/interface definition

    np_acts-logits-general · gemini-2.0-flash

    public class declarations

    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
     kasarigan
    -0.79
    migrationBuilder
    -0.70
    UnsafeEnabled
    -0.67
    richTextPanel
    -0.65
    IUrlHelper
    -0.65
     jsPsych
    -0.61
    TabIndex
    -0.56
     espagnole
    -0.56
    AndEndTag
    -0.56
     housewives
    -0.56
    POSITIVE LOGITS
     class
    0.95
    class
    0.71
     struct
    0.65
     interface
    0.61
    struct
    0.57
     className
    0.57
    interface
    0.52
     concept
    0.52
     classes
    0.52
    ]--;
    0.49
    Activations Density 0.124%

    No Known Activations