© 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. 7145
    Prev
    Next
    INDEX
    Explanations

    instances of various handler functions used in programming contexts

    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
     للمعارف
    -0.67
    andExpect
    -0.56
    grees
    -0.56
     Athe
    -0.55
     Liza
    -0.53
    buttonText
    -0.52
     Competi
    -0.51
     laziness
    -0.51
    thenReturn
    -0.51
    agree
    -0.50
    POSITIVE LOGITS
     handler
    2.13
    Handler
    2.06
    handler
    2.06
     handling
    2.05
     Handler
    2.03
     Handling
    2.02
    handling
    2.02
     handlers
    1.88
    Handling
    1.80
     HANDLING
    1.77
    Activations Density 0.085%

    No Known Activations