© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 13190
    Prev
    Next
    INDEX
    Explanations

    constructs related to constants and function pointers 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
     chiuso
    -0.51
    AccessorTable
    -0.47
    IsInitialized
    -0.46
    धि
    -0.45
     eterno
    -0.45
     égard
    -0.43
    ništvo
    -0.43
     Mühe
    -0.43
     esterno
    -0.43
     ?>>
    -0.43
    POSITIVE LOGITS
     lenker
    0.85
    WEBPACK
    0.77
    +#+
    0.67
    :+:
    0.66
    matchCondition
    0.64
     Савезне
    0.62
     فريبيس
    0.61
     متعلقه
    0.61
     Valdés
    0.58
    Viited
    0.57
    Activations Density 0.256%

    No Known Activations