© 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. 2-GEMMASCOPE-RES-16K
    6. 9031
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts used in code and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kubwa
    -0.43
     poffible
    -0.42
    anzo
    -0.41
    サキ
    -0.40
     directly
    -0.39
    Par
    -0.39
     amore
    -0.39
     Strahl
    -0.38
     przypadku
    -0.38
    isDefault
    -0.36
    POSITIVE LOGITS
    RectangleBorder
    1.15
    ReusableCell
    1.13
    ParallelGroup
    1.08
    setVerticalGroup
    1.05
    AutoScaleMode
    1.04
    AnchorStyles
    1.03
    ChildScrollView
    1.01
     שוליים
    0.98
     AssemblyVersion
    0.97
    ValueGeneration
    0.97
    Activations Density 2.585%

    No Known Activations