© 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. 15-GEMMASCOPE-RES-16K
    11. 878
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and identifiers in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.97
    SpringBootTest
    -0.88
     سكانية
    -0.83
     nahilalakip
    -0.79
     kasarigan
    -0.75
     tartalomajánló
    -0.74
    IUrlHelper
    -0.74
    ContentAlignment
    -0.73
    ViewFeatures
    -0.73
     referenties
    -0.73
    POSITIVE LOGITS
     a
    0.45
    (),
    0.43
    íses
    0.42
    ();
    0.41
     in
    0.41
    */,
    0.41
     to
    0.40
    ing
    0.40
     noten
    0.40
    かに
    0.39
    Activations Density 0.049%

    No Known Activations