© 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. 10-GEMMASCOPE-RES-16K
    6. 8788
    Prev
    Next
    INDEX
    Explanations

    function definitions and their structure 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 @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imprend
    -0.40
     funghi
    -0.40
     negotiated
    -0.40
     rendel
    -0.39
     Headache
    -0.38
     Lupus
    -0.36
     sna
    -0.35
    ker
    -0.35
    Resolve
    -0.35
    pluck
    -0.34
    POSITIVE LOGITS
    WebVitals
    1.17
    PerformLayout
    1.10
    RenderAtEndOf
    1.01
    WaitGroup
    0.98
    AndEndTag
    0.97
    Personendaten
    0.96
    <()>
    0.91
    LookAnd
    0.89
    IGraphics
    0.88
    DeleteBehavior
    0.88
    Activations Density 0.192%

    No Known Activations