© 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. 2240
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming, specifically in the context of LLVM and its components

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

    Code snippets related to LLVM

    np_acts-logits-general · gemini-2.0-flash

    LLVM compiler infrastructure C++ code

    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
     Reform
    -0.88
     reform
    -0.85
    Reform
    -0.77
    reform
    -0.71
     reforms
    -0.69
     reformer
    -0.68
     reformers
    -0.62
     Reforms
    -0.56
     reforma
    -0.56
     reforming
    -0.55
    POSITIVE LOGITS
     LLVM
    0.77
     llvm
    0.75
    ंदीखरीदारी
    0.71
     المعيارى
    0.68
     مرئيه
    0.63
     صوتيه
    0.63
    EndGlobalSection
    0.62
     orizz
    0.60
    Rhestr
    0.60
    ])));
    0.59
    Activations Density 0.310%

    No Known Activations