© 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. 4-GEMMASCOPE-RES-16K
    11. 11424
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and macro definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sensibilité
    -0.59
     Turquie
    -0.59
     Beding
    -0.54
     arriva
    -0.54
     médec
    -0.53
     ferdig
    -0.52
     simplu
    -0.52
     registrazione
    -0.52
     sebaliknya
    -0.52
     Corée
    -0.51
    POSITIVE LOGITS
    (__
    1.75
    GroupLayout
    1.05
     (__
    1.00
    ($__
    0.88
    InstanceState
    0.87
    TagMode
    0.83
    numerusform
    0.81
    DebuggerNonUser
    0.78
    openzeppelin
    0.78
    новништво
    0.77
    Activations Density 0.015%

    No Known Activations