© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1853
    Prev
    Next
    INDEX
    Explanations

    code control structures and conditional statements

    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
    fjspx
    -0.87
    LLocation
    -0.64
     Paglinawan
    -0.61
     للاسماء
    -0.61
    tonsoft
    -0.59
    ImageContext
    -0.59
     Biôgrafia
    -0.59
    ViewFeatures
    -0.57
     AssemblyTitle
    -0.56
    SourceChecksum
    -0.56
    POSITIVE LOGITS
    continue
    0.81
    return
    0.78
     return
    0.72
     returned
    0.64
     continue
    0.63
     demografica
    0.62
    runApp
    0.56
     RETURN
    0.54
     returns
    0.54
     CONTINUE
    0.52
    Activations Density 0.198%

    No Known Activations