Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12935
    Prev
    Next
    INDEX
    Explanations

    instances of import statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pngtree
    -0.69
     ERS
    -0.68
     atof
    -0.66
     Pliny
    -0.66
     Mahomet
    -0.65
     entanto
    -0.65
     ſame
    -0.65
     juſt
    -0.64
    ControllerAdvice
    -0.64
    ed
    -0.64
    POSITIVE LOGITS
     import
    1.29
     *
    
    1.03
    import
    1.03
     Import
    0.95
     importación
    0.80
     imports
    0.79
    imports
    0.77
    ]))
    
    0.77
    '])){
    
    0.76
    ))))
    0.75
    Activations Density 0.010%

    No Known Activations