© 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. 3-GEMMASCOPE-RES-16K
    6. 612
    Prev
    Next
    INDEX
    Explanations

    calls to methods related to object allocation and view inflation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.90
    didSet
    -0.88
    featureID
    -0.82
     ThemeData
    -0.79
     Agamemnon
    -0.76
    principalTable
    -0.75
    dersfield
    -0.74
     PriorityQueue
    -0.73
    HasForeignKey
    -0.73
     kasarigan
    -0.73
    POSITIVE LOGITS
    LayoutInflater
    1.21
     alloc
    0.99
    Inflater
    0.81
     LayoutInflater
    0.79
    inflater
    0.69
     inflater
    0.66
    spath
    0.66
    IMPORTED
    0.62
     xmlns
    0.58
    alloc
    0.55
    Activations Density 0.012%

    No Known Activations