© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    class definitions and their attributes in programming code

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

    Code related to class or interface definitions

    np_acts-logits-general · gemini-2.0-flash

    public followed by class or interface

    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
    rungsseite
    -0.59
     resourceCulture
    -0.47
    지를
    -0.46
    LayoutPanel
    -0.45
     fo
    -0.44
     jalur
    -0.41
     IndexPath
    -0.40
    EndContext
    -0.40
     JMenuItem
    -0.40
    contentLoaded
    -0.39
    POSITIVE LOGITS
     nakalista
    0.97
    class
    0.87
     class
    0.81
     instanceof
    0.76
     isinstance
    0.76
     extends
    0.69
     Baillargeon
    0.68
     ویکی‌آمباردا
    0.65
    ArgsConstructor
    0.64
    modb
    0.63
    Activations Density 0.101%

    No Known Activations