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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1268
    Prev
    Next
    INDEX
    Explanations

    elements related to assembly attributes in programming contexts

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

    software assemblies

    np_acts-logits-general · gemini-2.0-flash

    .NET assemblies

    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
     myſelf
    -0.91
     himſelf
    -0.81
     themſelves
    -0.80
     Etr
    -0.76
     itſelf
    -0.75
     becauſe
    -0.74
     Monfieur
    -0.74
    Hochspringen
    -0.73
     Shakspeare
    -0.73
     PhpStorm
    -0.72
    POSITIVE LOGITS
     Assembly
    0.94
     assembly
    0.92
    assembly
    0.86
    Assembly
    0.80
     ASSEMBLY
    0.77
     AssemblyVersion
    0.71
     assemblies
    0.63
     Assemblies
    0.55
    <eos>
    0.54
    loaded
    0.49
    Activations Density 0.033%

    No Known Activations