© 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. 12-GEMMASCOPE-RES-16K
    11. 10951
    Prev
    Next
    INDEX
    Explanations

    function calls and variable assignments related to programming tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.75
     autorytatywna
    -0.74
     &___
    -0.69
    IUrlHelper
    -0.69
    SpringBootTest
    -0.66
     Савезне
    -0.64
    CodeAttribute
    -0.64
     مرئيه
    -0.63
     виправивши
    -0.63
    WriteAttribute
    -0.62
    POSITIVE LOGITS
    +#+#
    0.61
    nativeElement
    0.61
    PerformLayout
    0.61
     myſelf
    0.59
    stretchr
    0.59
    enumi
    0.58
    mặt
    0.57
    ूरत
    0.56
     houſe
    0.53
    cplusplus
    0.53
    Activations Density 0.172%

    No Known Activations