© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    programming-related concepts and coding practices

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

    Code-related terms and function/method calls

    np_acts-logits-general · gemini-2.0-flash

    calling methods

    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
    mybatisplus
    -0.73
     CWE
    -0.68
    ViewFeatures
    -0.66
     autorytatywna
    -0.61
     sqlalchemy
    -0.60
     lenker
    -0.59
     endwhile
    -0.59
    EndGlobalSection
    -0.55
     surla
    -0.55
     bVar
    -0.55
    POSITIVE LOGITS
     {@
    0.81
     `
    0.65
     funkci
    0.64
    <code>
    0.62
     _
    0.57
     calling
    0.56
     fungsi
    0.54
     inimes
    0.54
     Calling
    0.53
     funkce
    0.53
    Activations Density 1.161%

    No Known Activations